コード例 #1
0
ファイル: lmvmimpl.c プロジェクト: firedrakeproject/petsc
static PetscErrorCode MatCopy_LMVM(Mat B, Mat M, MatStructure str)
{
  Mat_LMVM          *bctx = (Mat_LMVM*)B->data;
  Mat_LMVM          *mctx;
  PetscErrorCode    ierr;
  PetscInt          i;
  PetscBool         allocatedM;

  PetscFunctionBegin;
  if (str == DIFFERENT_NONZERO_PATTERN) {
    ierr = MatLMVMReset(M, PETSC_TRUE);CHKERRQ(ierr);
    ierr = MatLMVMAllocate(M, bctx->Xprev, bctx->Fprev);CHKERRQ(ierr);
  } else {
    ierr = MatLMVMIsAllocated(M, &allocatedM);CHKERRQ(ierr);
    if (!allocatedM) SETERRQ(PetscObjectComm((PetscObject)B), PETSC_ERR_ARG_WRONGSTATE, "Target matrix must be allocated first");
    MatCheckSameSize(B, 1, M, 2);
  }
  
  mctx = (Mat_LMVM*)M->data;
  if (bctx->user_pc) {
    ierr = MatLMVMSetJ0PC(M, bctx->J0pc);CHKERRQ(ierr);
  } else if (bctx->user_ksp) {
    ierr = MatLMVMSetJ0KSP(M, bctx->J0ksp);CHKERRQ(ierr);
  } else if (bctx->J0) {
    ierr = MatLMVMSetJ0(M, bctx->J0);CHKERRQ(ierr);
  } else if (bctx->user_scale) {
    if (bctx->J0diag) {
      ierr = MatLMVMSetJ0Diag(M, bctx->J0diag);CHKERRQ(ierr);
    } else {
      ierr = MatLMVMSetJ0Scale(M, bctx->J0scalar);CHKERRQ(ierr);
    }
  }
  mctx->nupdates = bctx->nupdates;
  mctx->nrejects = bctx->nrejects;
  mctx->k = bctx->k;
  for (i=0; i<=bctx->k; ++i) {
    ierr = VecCopy(bctx->S[i], mctx->S[i]);CHKERRQ(ierr);
    ierr = VecCopy(bctx->Y[i], mctx->Y[i]);CHKERRQ(ierr);
    ierr = VecCopy(bctx->Xprev, mctx->Xprev);CHKERRQ(ierr);
    ierr = VecCopy(bctx->Fprev, mctx->Fprev);CHKERRQ(ierr);
  }
  if (bctx->ops->copy) {
    ierr = (*bctx->ops->copy)(B, M, str);CHKERRQ(ierr);
  }
  PetscFunctionReturn(0);
}
コード例 #2
0
ファイル: lmvmimpl.c プロジェクト: firedrakeproject/petsc
PetscErrorCode MatAllocate_LMVM(Mat B, Vec X, Vec F)
{
  Mat_LMVM          *lmvm = (Mat_LMVM*)B->data;
  PetscErrorCode    ierr;
  PetscBool         same, allocate = PETSC_FALSE;
  PetscInt          m, n, M, N;
  VecType           type;

  PetscFunctionBegin;
  if (lmvm->allocated) {
    VecCheckMatCompatible(B, X, 2, F, 3);
    ierr = VecGetType(X, &type);CHKERRQ(ierr);
    ierr = PetscObjectTypeCompare((PetscObject)lmvm->Xprev, type, &same);CHKERRQ(ierr);
    if (!same) {
      /* Given X vector has a different type than allocated X-type data structures.
         We need to destroy all of this and duplicate again out of the given vector. */
      allocate = PETSC_TRUE;
      ierr = MatLMVMReset(B, PETSC_TRUE);CHKERRQ(ierr);
    }
  } else {
    allocate = PETSC_TRUE;
  }
  if (allocate) {
    ierr = VecGetLocalSize(X, &n);CHKERRQ(ierr);
    ierr = VecGetSize(X, &N);CHKERRQ(ierr);
    ierr = VecGetLocalSize(F, &m);CHKERRQ(ierr);
    ierr = VecGetSize(F, &M);CHKERRQ(ierr);
    ierr = MatSetSizes(B, m, n, M, N);CHKERRQ(ierr);
    ierr = PetscLayoutSetUp(B->rmap);CHKERRQ(ierr);
    ierr = PetscLayoutSetUp(B->cmap);CHKERRQ(ierr);
    ierr = VecDuplicate(X, &lmvm->Xprev);CHKERRQ(ierr);
    ierr = VecDuplicate(F, &lmvm->Fprev);CHKERRQ(ierr);
    if (lmvm->m > 0) {
      ierr = VecDuplicateVecs(lmvm->Xprev, lmvm->m, &lmvm->S);CHKERRQ(ierr);
      ierr = VecDuplicateVecs(lmvm->Fprev, lmvm->m, &lmvm->Y);CHKERRQ(ierr);
    }
    lmvm->allocated = PETSC_TRUE;
    B->preallocated = PETSC_TRUE;
    B->assembled = PETSC_TRUE;
  }
  PetscFunctionReturn(0);
}
コード例 #3
0
ファイル: owlqn.c プロジェクト: OpenCMISS-Dependencies/petsc
static PetscErrorCode TaoSolve_OWLQN(Tao tao)
{
  TAO_OWLQN                    *lmP = (TAO_OWLQN *)tao->data;
  PetscReal                    f, fold, gdx, gnorm;
  PetscReal                    step = 1.0;
  PetscReal                    delta;
  PetscErrorCode               ierr;
  PetscInt                     stepType;
  PetscInt                     iter = 0;
  TaoConvergedReason           reason = TAO_CONTINUE_ITERATING;
  TaoLineSearchConvergedReason ls_status = TAOLINESEARCH_CONTINUE_ITERATING;

  PetscFunctionBegin;
  if (tao->XL || tao->XU || tao->ops->computebounds) {
    ierr = PetscPrintf(((PetscObject)tao)->comm,"WARNING: Variable bounds have been set but will be ignored by owlqn algorithm\n");CHKERRQ(ierr);
  }

  /* Check convergence criteria */
  ierr = TaoComputeObjectiveAndGradient(tao, tao->solution, &f, tao->gradient);CHKERRQ(ierr);

  ierr = VecCopy(tao->gradient, lmP->GV);CHKERRQ(ierr);

  ierr = ComputePseudoGrad_OWLQN(tao->solution,lmP->GV,lmP->lambda);CHKERRQ(ierr);

  ierr = VecNorm(lmP->GV,NORM_2,&gnorm);CHKERRQ(ierr);

  if (PetscIsInfOrNanReal(f) || PetscIsInfOrNanReal(gnorm)) SETERRQ(PETSC_COMM_SELF,1, "User provided compute function generated Inf or NaN");

  ierr = TaoMonitor(tao, iter, f, gnorm, 0.0, step, &reason);CHKERRQ(ierr);
  if (reason != TAO_CONTINUE_ITERATING) PetscFunctionReturn(0);

  /* Set initial scaling for the function */
  if (f != 0.0) {
    delta = 2.0 * PetscAbsScalar(f) / (gnorm*gnorm);
  } else {
    delta = 2.0 / (gnorm*gnorm);
  }
  ierr = MatLMVMSetDelta(lmP->M,delta);CHKERRQ(ierr);

  /* Set counter for gradient/reset steps */
  lmP->bfgs = 0;
  lmP->sgrad = 0;
  lmP->grad = 0;

  /* Have not converged; continue with Newton method */
  while (reason == TAO_CONTINUE_ITERATING) {
    /* Compute direction */
    ierr = MatLMVMUpdate(lmP->M,tao->solution,tao->gradient);CHKERRQ(ierr);
    ierr = MatLMVMSolve(lmP->M, lmP->GV, lmP->D);CHKERRQ(ierr);

    ierr = ProjDirect_OWLQN(lmP->D,lmP->GV);CHKERRQ(ierr);

    ++lmP->bfgs;

    /* Check for success (descent direction) */
    ierr = VecDot(lmP->D, lmP->GV , &gdx);CHKERRQ(ierr);
    if ((gdx <= 0.0) || PetscIsInfOrNanReal(gdx)) {

      /* Step is not descent or direction produced not a number
         We can assert bfgsUpdates > 1 in this case because
         the first solve produces the scaled gradient direction,
         which is guaranteed to be descent

         Use steepest descent direction (scaled) */
      ++lmP->grad;

      if (f != 0.0) {
        delta = 2.0 * PetscAbsScalar(f) / (gnorm*gnorm);
      } else {
        delta = 2.0 / (gnorm*gnorm);
      }
      ierr = MatLMVMSetDelta(lmP->M, delta);CHKERRQ(ierr);
      ierr = MatLMVMReset(lmP->M);CHKERRQ(ierr);
      ierr = MatLMVMUpdate(lmP->M, tao->solution, tao->gradient);CHKERRQ(ierr);
      ierr = MatLMVMSolve(lmP->M,lmP->GV, lmP->D);CHKERRQ(ierr);

      ierr = ProjDirect_OWLQN(lmP->D,lmP->GV);CHKERRQ(ierr);

      lmP->bfgs = 1;
      ++lmP->sgrad;
      stepType = OWLQN_SCALED_GRADIENT;
    } else {
      if (1 == lmP->bfgs) {
        /* The first BFGS direction is always the scaled gradient */
        ++lmP->sgrad;
        stepType = OWLQN_SCALED_GRADIENT;
      } else {
        ++lmP->bfgs;
        stepType = OWLQN_BFGS;
      }
    }

    ierr = VecScale(lmP->D, -1.0);CHKERRQ(ierr);

    /* Perform the linesearch */
    fold = f;
    ierr = VecCopy(tao->solution, lmP->Xold);CHKERRQ(ierr);
    ierr = VecCopy(tao->gradient, lmP->Gold);CHKERRQ(ierr);

    ierr = TaoLineSearchApply(tao->linesearch, tao->solution, &f, lmP->GV, lmP->D, &step,&ls_status);CHKERRQ(ierr);
    ierr = TaoAddLineSearchCounts(tao);CHKERRQ(ierr);

    while (((int)ls_status < 0) && (stepType != OWLQN_GRADIENT)) {

      /* Reset factors and use scaled gradient step */
      f = fold;
      ierr = VecCopy(lmP->Xold, tao->solution);CHKERRQ(ierr);
      ierr = VecCopy(lmP->Gold, tao->gradient);CHKERRQ(ierr);
      ierr = VecCopy(tao->gradient, lmP->GV);CHKERRQ(ierr);

      ierr = ComputePseudoGrad_OWLQN(tao->solution,lmP->GV,lmP->lambda);CHKERRQ(ierr);

      switch(stepType) {
      case OWLQN_BFGS:
        /* Failed to obtain acceptable iterate with BFGS step
           Attempt to use the scaled gradient direction */

        if (f != 0.0) {
          delta = 2.0 * PetscAbsScalar(f) / (gnorm*gnorm);
        } else {
          delta = 2.0 / (gnorm*gnorm);
        }
        ierr = MatLMVMSetDelta(lmP->M, delta);CHKERRQ(ierr);
        ierr = MatLMVMReset(lmP->M);CHKERRQ(ierr);
        ierr = MatLMVMUpdate(lmP->M, tao->solution, tao->gradient);CHKERRQ(ierr);
        ierr = MatLMVMSolve(lmP->M, lmP->GV, lmP->D);CHKERRQ(ierr);

        ierr = ProjDirect_OWLQN(lmP->D,lmP->GV);CHKERRQ(ierr);

        lmP->bfgs = 1;
        ++lmP->sgrad;
        stepType = OWLQN_SCALED_GRADIENT;
        break;

      case OWLQN_SCALED_GRADIENT:
        /* The scaled gradient step did not produce a new iterate;
           attempt to use the gradient direction.
           Need to make sure we are not using a different diagonal scaling */
        ierr = MatLMVMSetDelta(lmP->M, 1.0);CHKERRQ(ierr);
        ierr = MatLMVMReset(lmP->M);CHKERRQ(ierr);
        ierr = MatLMVMUpdate(lmP->M, tao->solution, tao->gradient);CHKERRQ(ierr);
        ierr = MatLMVMSolve(lmP->M, lmP->GV, lmP->D);CHKERRQ(ierr);

        ierr = ProjDirect_OWLQN(lmP->D,lmP->GV);CHKERRQ(ierr);

        lmP->bfgs = 1;
        ++lmP->grad;
        stepType = OWLQN_GRADIENT;
        break;
      }
      ierr = VecScale(lmP->D, -1.0);CHKERRQ(ierr);


      /* Perform the linesearch */
      ierr = TaoLineSearchApply(tao->linesearch, tao->solution, &f, lmP->GV, lmP->D, &step, &ls_status);CHKERRQ(ierr);
      ierr = TaoAddLineSearchCounts(tao);CHKERRQ(ierr);
    }

    if ((int)ls_status < 0) {
      /* Failed to find an improving point*/
      f = fold;
      ierr = VecCopy(lmP->Xold, tao->solution);CHKERRQ(ierr);
      ierr = VecCopy(lmP->Gold, tao->gradient);CHKERRQ(ierr);
      ierr = VecCopy(tao->gradient, lmP->GV);CHKERRQ(ierr);
      step = 0.0;
    } else {
      /* a little hack here, because that gv is used to store g */
      ierr = VecCopy(lmP->GV, tao->gradient);CHKERRQ(ierr);
    }

    ierr = ComputePseudoGrad_OWLQN(tao->solution,lmP->GV,lmP->lambda);CHKERRQ(ierr);

    /* Check for termination */

    ierr = VecNorm(lmP->GV,NORM_2,&gnorm);CHKERRQ(ierr);

    iter++;
    ierr = TaoMonitor(tao,iter,f,gnorm,0.0,step,&reason);CHKERRQ(ierr);

    if ((int)ls_status < 0) break;
  }
  PetscFunctionReturn(0);
}
コード例 #4
0
ファイル: ntr.c プロジェクト: PeiLiu90/petsc
static PetscErrorCode TaoSolve_NTR(Tao tao)
{
  TAO_NTR            *tr = (TAO_NTR *)tao->data;
  PC                 pc;
  KSPConvergedReason ksp_reason;
  TaoConvergedReason reason;
  PetscReal          fmin, ftrial, prered, actred, kappa, sigma, beta;
  PetscReal          tau, tau_1, tau_2, tau_max, tau_min, max_radius;
  PetscReal          f, gnorm;

  PetscReal          delta;
  PetscReal          norm_d;
  PetscErrorCode     ierr;
  PetscInt           iter = 0;
  PetscInt           bfgsUpdates = 0;
  PetscInt           needH;

  PetscInt           i_max = 5;
  PetscInt           j_max = 1;
  PetscInt           i, j, N, n, its;

  PetscFunctionBegin;
  if (tao->XL || tao->XU || tao->ops->computebounds) {
    ierr = PetscPrintf(((PetscObject)tao)->comm,"WARNING: Variable bounds have been set but will be ignored by ntr algorithm\n");CHKERRQ(ierr);
  }

  tao->trust = tao->trust0;

  /* Modify the radius if it is too large or small */
  tao->trust = PetscMax(tao->trust, tr->min_radius);
  tao->trust = PetscMin(tao->trust, tr->max_radius);


  if (NTR_PC_BFGS == tr->pc_type && !tr->M) {
    ierr = VecGetLocalSize(tao->solution,&n);CHKERRQ(ierr);
    ierr = VecGetSize(tao->solution,&N);CHKERRQ(ierr);
    ierr = MatCreateLMVM(((PetscObject)tao)->comm,n,N,&tr->M);CHKERRQ(ierr);
    ierr = MatLMVMAllocateVectors(tr->M,tao->solution);CHKERRQ(ierr);
  }

  /* Check convergence criteria */
  ierr = TaoComputeObjectiveAndGradient(tao, tao->solution, &f, tao->gradient);CHKERRQ(ierr);
  ierr = VecNorm(tao->gradient,NORM_2,&gnorm);CHKERRQ(ierr);
  if (PetscIsInfOrNanReal(f) || PetscIsInfOrNanReal(gnorm)) SETERRQ(PETSC_COMM_SELF,1, "User provided compute function generated Inf or NaN");
  needH = 1;

  ierr = TaoMonitor(tao, iter, f, gnorm, 0.0, 1.0, &reason);CHKERRQ(ierr);
  if (reason != TAO_CONTINUE_ITERATING) PetscFunctionReturn(0);

  /* Create vectors for the limited memory preconditioner */
  if ((NTR_PC_BFGS == tr->pc_type) &&
      (BFGS_SCALE_BFGS != tr->bfgs_scale_type)) {
    if (!tr->Diag) {
        ierr = VecDuplicate(tao->solution, &tr->Diag);CHKERRQ(ierr);
    }
  }

  switch(tr->ksp_type) {
  case NTR_KSP_NASH:
    ierr = KSPSetType(tao->ksp, KSPNASH);CHKERRQ(ierr);
    if (tao->ksp->ops->setfromoptions) {
      (*tao->ksp->ops->setfromoptions)(tao->ksp);
    }
    break;

  case NTR_KSP_STCG:
    ierr = KSPSetType(tao->ksp, KSPSTCG);CHKERRQ(ierr);
    if (tao->ksp->ops->setfromoptions) {
      (*tao->ksp->ops->setfromoptions)(tao->ksp);
    }
    break;

  default:
    ierr = KSPSetType(tao->ksp, KSPGLTR);CHKERRQ(ierr);
    if (tao->ksp->ops->setfromoptions) {
      (*tao->ksp->ops->setfromoptions)(tao->ksp);
    }
    break;
  }

  /*  Modify the preconditioner to use the bfgs approximation */
  ierr = KSPGetPC(tao->ksp, &pc);CHKERRQ(ierr);
  switch(tr->pc_type) {
  case NTR_PC_NONE:
    ierr = PCSetType(pc, PCNONE);CHKERRQ(ierr);
    if (pc->ops->setfromoptions) {
      (*pc->ops->setfromoptions)(pc);
    }
    break;

  case NTR_PC_AHESS:
    ierr = PCSetType(pc, PCJACOBI);CHKERRQ(ierr);
    if (pc->ops->setfromoptions) {
      (*pc->ops->setfromoptions)(pc);
    }
    ierr = PCJacobiSetUseAbs(pc);CHKERRQ(ierr);
    break;

  case NTR_PC_BFGS:
    ierr = PCSetType(pc, PCSHELL);CHKERRQ(ierr);
    if (pc->ops->setfromoptions) {
      (*pc->ops->setfromoptions)(pc);
    }
    ierr = PCShellSetName(pc, "bfgs");CHKERRQ(ierr);
    ierr = PCShellSetContext(pc, tr->M);CHKERRQ(ierr);
    ierr = PCShellSetApply(pc, MatLMVMSolveShell);CHKERRQ(ierr);
    break;

  default:
    /*  Use the pc method set by pc_type */
    break;
  }

  /*  Initialize trust-region radius */
  switch(tr->init_type) {
  case NTR_INIT_CONSTANT:
    /*  Use the initial radius specified */
    break;

  case NTR_INIT_INTERPOLATION:
    /*  Use the initial radius specified */
    max_radius = 0.0;

    for (j = 0; j < j_max; ++j) {
      fmin = f;
      sigma = 0.0;

      if (needH) {
        ierr = TaoComputeHessian(tao,tao->solution,tao->hessian,tao->hessian_pre);CHKERRQ(ierr);
        needH = 0;
      }

      for (i = 0; i < i_max; ++i) {

        ierr = VecCopy(tao->solution, tr->W);CHKERRQ(ierr);
        ierr = VecAXPY(tr->W, -tao->trust/gnorm, tao->gradient);CHKERRQ(ierr);
        ierr = TaoComputeObjective(tao, tr->W, &ftrial);CHKERRQ(ierr);

        if (PetscIsInfOrNanReal(ftrial)) {
          tau = tr->gamma1_i;
        }
        else {
          if (ftrial < fmin) {
            fmin = ftrial;
            sigma = -tao->trust / gnorm;
          }

          ierr = MatMult(tao->hessian, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
          ierr = VecDot(tao->gradient, tao->stepdirection, &prered);CHKERRQ(ierr);

          prered = tao->trust * (gnorm - 0.5 * tao->trust * prered / (gnorm * gnorm));
          actred = f - ftrial;
          if ((PetscAbsScalar(actred) <= tr->epsilon) &&
              (PetscAbsScalar(prered) <= tr->epsilon)) {
            kappa = 1.0;
          }
          else {
            kappa = actred / prered;
          }

          tau_1 = tr->theta_i * gnorm * tao->trust / (tr->theta_i * gnorm * tao->trust + (1.0 - tr->theta_i) * prered - actred);
          tau_2 = tr->theta_i * gnorm * tao->trust / (tr->theta_i * gnorm * tao->trust - (1.0 + tr->theta_i) * prered + actred);
          tau_min = PetscMin(tau_1, tau_2);
          tau_max = PetscMax(tau_1, tau_2);

          if (PetscAbsScalar(kappa - 1.0) <= tr->mu1_i) {
            /*  Great agreement */
            max_radius = PetscMax(max_radius, tao->trust);

            if (tau_max < 1.0) {
              tau = tr->gamma3_i;
            }
            else if (tau_max > tr->gamma4_i) {
              tau = tr->gamma4_i;
            }
            else {
              tau = tau_max;
            }
          }
          else if (PetscAbsScalar(kappa - 1.0) <= tr->mu2_i) {
            /*  Good agreement */
            max_radius = PetscMax(max_radius, tao->trust);

            if (tau_max < tr->gamma2_i) {
              tau = tr->gamma2_i;
            }
            else if (tau_max > tr->gamma3_i) {
              tau = tr->gamma3_i;
            }
            else {
              tau = tau_max;
            }
          }
          else {
            /*  Not good agreement */
            if (tau_min > 1.0) {
              tau = tr->gamma2_i;
            }
            else if (tau_max < tr->gamma1_i) {
              tau = tr->gamma1_i;
            }
            else if ((tau_min < tr->gamma1_i) && (tau_max >= 1.0)) {
              tau = tr->gamma1_i;
            }
            else if ((tau_1 >= tr->gamma1_i) && (tau_1 < 1.0) &&
                     ((tau_2 < tr->gamma1_i) || (tau_2 >= 1.0))) {
              tau = tau_1;
            }
            else if ((tau_2 >= tr->gamma1_i) && (tau_2 < 1.0) &&
                     ((tau_1 < tr->gamma1_i) || (tau_2 >= 1.0))) {
              tau = tau_2;
            }
            else {
              tau = tau_max;
            }
          }
        }
        tao->trust = tau * tao->trust;
      }

      if (fmin < f) {
        f = fmin;
        ierr = VecAXPY(tao->solution, sigma, tao->gradient);CHKERRQ(ierr);
        ierr = TaoComputeGradient(tao,tao->solution, tao->gradient);CHKERRQ(ierr);

        ierr = VecNorm(tao->gradient, NORM_2, &gnorm);CHKERRQ(ierr);

        if (PetscIsInfOrNanReal(f) || PetscIsInfOrNanReal(gnorm)) SETERRQ(PETSC_COMM_SELF,1, "User provided compute function generated Inf or NaN");
        needH = 1;

        ierr = TaoMonitor(tao, iter, f, gnorm, 0.0, 1.0, &reason);CHKERRQ(ierr);
        if (reason != TAO_CONTINUE_ITERATING) {
          PetscFunctionReturn(0);
        }
      }
    }
    tao->trust = PetscMax(tao->trust, max_radius);

    /*  Modify the radius if it is too large or small */
    tao->trust = PetscMax(tao->trust, tr->min_radius);
    tao->trust = PetscMin(tao->trust, tr->max_radius);
    break;

  default:
    /*  Norm of the first direction will initialize radius */
    tao->trust = 0.0;
    break;
  }

  /* Set initial scaling for the BFGS preconditioner
     This step is done after computing the initial trust-region radius
     since the function value may have decreased */
  if (NTR_PC_BFGS == tr->pc_type) {
    if (f != 0.0) {
      delta = 2.0 * PetscAbsScalar(f) / (gnorm*gnorm);
    }
    else {
      delta = 2.0 / (gnorm*gnorm);
    }
    ierr = MatLMVMSetDelta(tr->M,delta);CHKERRQ(ierr);
  }

  /* Have not converged; continue with Newton method */
  while (reason == TAO_CONTINUE_ITERATING) {
    ++iter;
    tao->ksp_its=0;
    /* Compute the Hessian */
    if (needH) {
      ierr = TaoComputeHessian(tao,tao->solution,tao->hessian,tao->hessian_pre);CHKERRQ(ierr);
      needH = 0;
    }

    if (NTR_PC_BFGS == tr->pc_type) {
      if (BFGS_SCALE_AHESS == tr->bfgs_scale_type) {
        /* Obtain diagonal for the bfgs preconditioner */
        ierr = MatGetDiagonal(tao->hessian, tr->Diag);CHKERRQ(ierr);
        ierr = VecAbs(tr->Diag);CHKERRQ(ierr);
        ierr = VecReciprocal(tr->Diag);CHKERRQ(ierr);
        ierr = MatLMVMSetScale(tr->M,tr->Diag);CHKERRQ(ierr);
      }

      /* Update the limited memory preconditioner */
      ierr = MatLMVMUpdate(tr->M, tao->solution, tao->gradient);CHKERRQ(ierr);
      ++bfgsUpdates;
    }

    while (reason == TAO_CONTINUE_ITERATING) {
      ierr = KSPSetOperators(tao->ksp, tao->hessian, tao->hessian_pre);CHKERRQ(ierr);

      /* Solve the trust region subproblem */
      if (NTR_KSP_NASH == tr->ksp_type) {
        ierr = KSPNASHSetRadius(tao->ksp,tao->trust);CHKERRQ(ierr);
        ierr = KSPSolve(tao->ksp, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
        ierr = KSPGetIterationNumber(tao->ksp,&its);CHKERRQ(ierr);
        tao->ksp_its+=its;
        tao->ksp_tot_its+=its;
        ierr = KSPNASHGetNormD(tao->ksp, &norm_d);CHKERRQ(ierr);
      } else if (NTR_KSP_STCG == tr->ksp_type) {
        ierr = KSPSTCGSetRadius(tao->ksp,tao->trust);CHKERRQ(ierr);
        ierr = KSPSolve(tao->ksp, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
        ierr = KSPGetIterationNumber(tao->ksp,&its);CHKERRQ(ierr);
        tao->ksp_its+=its;
        tao->ksp_tot_its+=its;
        ierr = KSPSTCGGetNormD(tao->ksp, &norm_d);CHKERRQ(ierr);
      } else { /* NTR_KSP_GLTR */
        ierr = KSPGLTRSetRadius(tao->ksp,tao->trust);CHKERRQ(ierr);
        ierr = KSPSolve(tao->ksp, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
        ierr = KSPGetIterationNumber(tao->ksp,&its);CHKERRQ(ierr);
        tao->ksp_its+=its;
        tao->ksp_tot_its+=its;
        ierr = KSPGLTRGetNormD(tao->ksp, &norm_d);CHKERRQ(ierr);
      }

      if (0.0 == tao->trust) {
        /* Radius was uninitialized; use the norm of the direction */
        if (norm_d > 0.0) {
          tao->trust = norm_d;

          /* Modify the radius if it is too large or small */
          tao->trust = PetscMax(tao->trust, tr->min_radius);
          tao->trust = PetscMin(tao->trust, tr->max_radius);
        }
        else {
          /* The direction was bad; set radius to default value and re-solve
             the trust-region subproblem to get a direction */
          tao->trust = tao->trust0;

          /* Modify the radius if it is too large or small */
          tao->trust = PetscMax(tao->trust, tr->min_radius);
          tao->trust = PetscMin(tao->trust, tr->max_radius);

          if (NTR_KSP_NASH == tr->ksp_type) {
            ierr = KSPNASHSetRadius(tao->ksp,tao->trust);CHKERRQ(ierr);
            ierr = KSPSolve(tao->ksp, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
            ierr = KSPGetIterationNumber(tao->ksp,&its);CHKERRQ(ierr);
            tao->ksp_its+=its;
            tao->ksp_tot_its+=its;
            ierr = KSPNASHGetNormD(tao->ksp, &norm_d);CHKERRQ(ierr);
          } else if (NTR_KSP_STCG == tr->ksp_type) {
            ierr = KSPSTCGSetRadius(tao->ksp,tao->trust);CHKERRQ(ierr);
            ierr = KSPSolve(tao->ksp, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
            ierr = KSPGetIterationNumber(tao->ksp,&its);CHKERRQ(ierr);
            tao->ksp_its+=its;
            tao->ksp_tot_its+=its;
            ierr = KSPSTCGGetNormD(tao->ksp, &norm_d);CHKERRQ(ierr);
          } else { /* NTR_KSP_GLTR */
            ierr = KSPGLTRSetRadius(tao->ksp,tao->trust);CHKERRQ(ierr);
            ierr = KSPSolve(tao->ksp, tao->gradient, tao->stepdirection);CHKERRQ(ierr);
            ierr = KSPGetIterationNumber(tao->ksp,&its);CHKERRQ(ierr);
            tao->ksp_its+=its;
            tao->ksp_tot_its+=its;
            ierr = KSPGLTRGetNormD(tao->ksp, &norm_d);CHKERRQ(ierr);
          }

          if (norm_d == 0.0) SETERRQ(PETSC_COMM_SELF,1, "Initial direction zero");
        }
      }
      ierr = VecScale(tao->stepdirection, -1.0);CHKERRQ(ierr);
      ierr = KSPGetConvergedReason(tao->ksp, &ksp_reason);CHKERRQ(ierr);
      if ((KSP_DIVERGED_INDEFINITE_PC == ksp_reason) &&
          (NTR_PC_BFGS == tr->pc_type) && (bfgsUpdates > 1)) {
        /* Preconditioner is numerically indefinite; reset the
           approximate if using BFGS preconditioning. */

        if (f != 0.0) {
          delta = 2.0 * PetscAbsScalar(f) / (gnorm*gnorm);
        }
        else {
          delta = 2.0 / (gnorm*gnorm);
        }
        ierr = MatLMVMSetDelta(tr->M, delta);CHKERRQ(ierr);
        ierr = MatLMVMReset(tr->M);CHKERRQ(ierr);
        ierr = MatLMVMUpdate(tr->M, tao->solution, tao->gradient);CHKERRQ(ierr);
        bfgsUpdates = 1;
      }

      if (NTR_UPDATE_REDUCTION == tr->update_type) {
        /* Get predicted reduction */
        if (NTR_KSP_NASH == tr->ksp_type) {
          ierr = KSPNASHGetObjFcn(tao->ksp,&prered);CHKERRQ(ierr);
        } else if (NTR_KSP_STCG == tr->ksp_type) {
          ierr = KSPSTCGGetObjFcn(tao->ksp,&prered);CHKERRQ(ierr);
        } else { /* gltr */
          ierr = KSPGLTRGetObjFcn(tao->ksp,&prered);CHKERRQ(ierr);
        }

        if (prered >= 0.0) {
          /* The predicted reduction has the wrong sign.  This cannot
             happen in infinite precision arithmetic.  Step should
             be rejected! */
          tao->trust = tr->alpha1 * PetscMin(tao->trust, norm_d);
        }
        else {
          /* Compute trial step and function value */
          ierr = VecCopy(tao->solution,tr->W);CHKERRQ(ierr);
          ierr = VecAXPY(tr->W, 1.0, tao->stepdirection);CHKERRQ(ierr);
          ierr = TaoComputeObjective(tao, tr->W, &ftrial);CHKERRQ(ierr);

          if (PetscIsInfOrNanReal(ftrial)) {
            tao->trust = tr->alpha1 * PetscMin(tao->trust, norm_d);
          } else {
            /* Compute and actual reduction */
            actred = f - ftrial;
            prered = -prered;
            if ((PetscAbsScalar(actred) <= tr->epsilon) &&
                (PetscAbsScalar(prered) <= tr->epsilon)) {
              kappa = 1.0;
            }
            else {
              kappa = actred / prered;
            }

            /* Accept or reject the step and update radius */
            if (kappa < tr->eta1) {
              /* Reject the step */
              tao->trust = tr->alpha1 * PetscMin(tao->trust, norm_d);
            }
            else {
              /* Accept the step */
              if (kappa < tr->eta2) {
                /* Marginal bad step */
                tao->trust = tr->alpha2 * PetscMin(tao->trust, norm_d);
              }
              else if (kappa < tr->eta3) {
                /* Reasonable step */
                tao->trust = tr->alpha3 * tao->trust;
              }
              else if (kappa < tr->eta4) {
                /* Good step */
                tao->trust = PetscMax(tr->alpha4 * norm_d, tao->trust);
              }
              else {
                /* Very good step */
                tao->trust = PetscMax(tr->alpha5 * norm_d, tao->trust);
              }
              break;
            }
          }
        }
      }
      else {
        /* Get predicted reduction */
        if (NTR_KSP_NASH == tr->ksp_type) {
          ierr = KSPNASHGetObjFcn(tao->ksp,&prered);CHKERRQ(ierr);
        } else if (NTR_KSP_STCG == tr->ksp_type) {
          ierr = KSPSTCGGetObjFcn(tao->ksp,&prered);CHKERRQ(ierr);
        } else { /* gltr */
          ierr = KSPGLTRGetObjFcn(tao->ksp,&prered);CHKERRQ(ierr);
        }

        if (prered >= 0.0) {
          /* The predicted reduction has the wrong sign.  This cannot
             happen in infinite precision arithmetic.  Step should
             be rejected! */
          tao->trust = tr->gamma1 * PetscMin(tao->trust, norm_d);
        }
        else {
          ierr = VecCopy(tao->solution, tr->W);CHKERRQ(ierr);
          ierr = VecAXPY(tr->W, 1.0, tao->stepdirection);CHKERRQ(ierr);
          ierr = TaoComputeObjective(tao, tr->W, &ftrial);CHKERRQ(ierr);
          if (PetscIsInfOrNanReal(ftrial)) {
            tao->trust = tr->gamma1 * PetscMin(tao->trust, norm_d);
          }
          else {
            ierr = VecDot(tao->gradient, tao->stepdirection, &beta);CHKERRQ(ierr);
            actred = f - ftrial;
            prered = -prered;
            if ((PetscAbsScalar(actred) <= tr->epsilon) &&
                (PetscAbsScalar(prered) <= tr->epsilon)) {
              kappa = 1.0;
            }
            else {
              kappa = actred / prered;
            }

            tau_1 = tr->theta * beta / (tr->theta * beta - (1.0 - tr->theta) * prered + actred);
            tau_2 = tr->theta * beta / (tr->theta * beta + (1.0 + tr->theta) * prered - actred);
            tau_min = PetscMin(tau_1, tau_2);
            tau_max = PetscMax(tau_1, tau_2);

            if (kappa >= 1.0 - tr->mu1) {
              /* Great agreement; accept step and update radius */
              if (tau_max < 1.0) {
                tao->trust = PetscMax(tao->trust, tr->gamma3 * norm_d);
              }
              else if (tau_max > tr->gamma4) {
                tao->trust = PetscMax(tao->trust, tr->gamma4 * norm_d);
              }
              else {
                tao->trust = PetscMax(tao->trust, tau_max * norm_d);
              }
              break;
            }
            else if (kappa >= 1.0 - tr->mu2) {
              /* Good agreement */

              if (tau_max < tr->gamma2) {
                tao->trust = tr->gamma2 * PetscMin(tao->trust, norm_d);
              }
              else if (tau_max > tr->gamma3) {
                tao->trust = PetscMax(tao->trust, tr->gamma3 * norm_d);
              }
              else if (tau_max < 1.0) {
                tao->trust = tau_max * PetscMin(tao->trust, norm_d);
              }
              else {
                tao->trust = PetscMax(tao->trust, tau_max * norm_d);
              }
              break;
            }
            else {
              /* Not good agreement */
              if (tau_min > 1.0) {
                tao->trust = tr->gamma2 * PetscMin(tao->trust, norm_d);
              }
              else if (tau_max < tr->gamma1) {
                tao->trust = tr->gamma1 * PetscMin(tao->trust, norm_d);
              }
              else if ((tau_min < tr->gamma1) && (tau_max >= 1.0)) {
                tao->trust = tr->gamma1 * PetscMin(tao->trust, norm_d);
              }
              else if ((tau_1 >= tr->gamma1) && (tau_1 < 1.0) &&
                       ((tau_2 < tr->gamma1) || (tau_2 >= 1.0))) {
                tao->trust = tau_1 * PetscMin(tao->trust, norm_d);
              }
              else if ((tau_2 >= tr->gamma1) && (tau_2 < 1.0) &&
                       ((tau_1 < tr->gamma1) || (tau_2 >= 1.0))) {
                tao->trust = tau_2 * PetscMin(tao->trust, norm_d);
              }
              else {
                tao->trust = tau_max * PetscMin(tao->trust, norm_d);
              }
            }
          }
        }
      }

      /* The step computed was not good and the radius was decreased.
         Monitor the radius to terminate. */
      ierr = TaoMonitor(tao, iter, f, gnorm, 0.0, tao->trust, &reason);CHKERRQ(ierr);
    }

    /* The radius may have been increased; modify if it is too large */
    tao->trust = PetscMin(tao->trust, tr->max_radius);

    if (reason == TAO_CONTINUE_ITERATING) {
      ierr = VecCopy(tr->W, tao->solution);CHKERRQ(ierr);
      f = ftrial;
      ierr = TaoComputeGradient(tao, tao->solution, tao->gradient);
      ierr = VecNorm(tao->gradient, NORM_2, &gnorm);CHKERRQ(ierr);
      if (PetscIsInfOrNanReal(f) || PetscIsInfOrNanReal(gnorm)) SETERRQ(PETSC_COMM_SELF,1, "User provided compute function generated Inf or NaN");
      needH = 1;
      ierr = TaoMonitor(tao, iter, f, gnorm, 0.0, tao->trust, &reason);CHKERRQ(ierr);
    }
  }
  PetscFunctionReturn(0);
}
コード例 #5
0
ファイル: lmvmmat.c プロジェクト: 00liujj/petsc
extern PetscErrorCode MatLMVMUpdate(Mat M, Vec x, Vec g)
{
  MatLMVMCtx     *ctx;
  PetscReal      rhotemp, rhotol;
  PetscReal      y0temp, s0temp;
  PetscReal      yDy, yDs, sDs;
  PetscReal      sigmanew, denom;
  PetscErrorCode ierr;
  PetscInt       i;
  PetscBool      same;
  PetscReal      yy_sum=0.0, ys_sum=0.0, ss_sum=0.0;

  PetscFunctionBegin;
  PetscValidHeaderSpecific(x,VEC_CLASSID,2);
  PetscValidHeaderSpecific(g,VEC_CLASSID,3);
  ierr = PetscObjectTypeCompare((PetscObject)M,MATSHELL,&same);CHKERRQ(ierr);
  if (!same) SETERRQ(PETSC_COMM_SELF,1,"Matrix M is not type MatLMVM");
  ierr = MatShellGetContext(M,(void**)&ctx);CHKERRQ(ierr);
  if (!ctx->allocated) {
    ierr = MatLMVMAllocateVectors(M, x); CHKERRQ(ierr);
  }

  if (0 == ctx->iter) {
    ierr = MatLMVMReset(M);CHKERRQ(ierr);
  }  else {
    ierr = VecAYPX(ctx->Gprev,-1.0,g);CHKERRQ(ierr);
    ierr = VecAYPX(ctx->Xprev,-1.0,x);CHKERRQ(ierr);

    ierr = VecDot(ctx->Gprev,ctx->Xprev,&rhotemp);CHKERRQ(ierr);
    ierr = VecDot(ctx->Gprev,ctx->Gprev,&y0temp);CHKERRQ(ierr);

    rhotol = ctx->eps * y0temp;
    if (rhotemp > rhotol) {
      ++ctx->nupdates;

      ctx->lmnow = PetscMin(ctx->lmnow+1, ctx->lm);
      ierr=PetscObjectDereference((PetscObject)ctx->S[ctx->lm]);CHKERRQ(ierr);
      ierr=PetscObjectDereference((PetscObject)ctx->Y[ctx->lm]);CHKERRQ(ierr);
      for (i = ctx->lm-1; i >= 0; --i) {
        ctx->S[i+1] = ctx->S[i];
        ctx->Y[i+1] = ctx->Y[i];
        ctx->rho[i+1] = ctx->rho[i];
      }
      ctx->S[0] = ctx->Xprev;
      ctx->Y[0] = ctx->Gprev;
      PetscObjectReference((PetscObject)ctx->S[0]);
      PetscObjectReference((PetscObject)ctx->Y[0]);
      ctx->rho[0] = 1.0 / rhotemp;

      /*  Compute the scaling */
      switch(ctx->scaleType) {
      case MatLMVM_Scale_None:
        break;

      case MatLMVM_Scale_Scalar:
        /*  Compute s^T s  */
          ierr = VecDot(ctx->Xprev,ctx->Xprev,&s0temp);CHKERRQ(ierr);

        /*  Scalar is positive; safeguards are not required. */

        /*  Save information for scalar scaling */
        ctx->yy_history[(ctx->nupdates - 1) % ctx->scalar_history] = y0temp;
        ctx->ys_history[(ctx->nupdates - 1) % ctx->scalar_history] = rhotemp;
        ctx->ss_history[(ctx->nupdates - 1) % ctx->scalar_history] = s0temp;

        /*  Compute summations for scalar scaling */
        yy_sum = 0;     /*  No safeguard required; y^T y > 0 */
        ys_sum = 0;     /*  No safeguard required; y^T s > 0 */
        ss_sum = 0;     /*  No safeguard required; s^T s > 0 */
        for (i = 0; i < PetscMin(ctx->nupdates, ctx->scalar_history); ++i) {
          yy_sum += ctx->yy_history[i];
          ys_sum += ctx->ys_history[i];
          ss_sum += ctx->ss_history[i];
        }

        if (0.0 == ctx->s_alpha) {
          /*  Safeguard ys_sum  */
          if (0.0 == ys_sum) {
            ys_sum = TAO_ZERO_SAFEGUARD;
          }

          sigmanew = ss_sum / ys_sum;
        } else if (1.0 == ctx->s_alpha) {
          /*  Safeguard yy_sum  */
          if (0.0 == yy_sum) {
            yy_sum = TAO_ZERO_SAFEGUARD;
          }

          sigmanew = ys_sum / yy_sum;
        } else {
          denom = 2*ctx->s_alpha*yy_sum;

          /*  Safeguard denom */
          if (0.0 == denom) {
            denom = TAO_ZERO_SAFEGUARD;
          }

          sigmanew = ((2*ctx->s_alpha-1)*ys_sum +  PetscSqrtScalar((2*ctx->s_alpha-1)*(2*ctx->s_alpha-1)*ys_sum*ys_sum - 4*(ctx->s_alpha)*(ctx->s_alpha-1)*yy_sum*ss_sum)) / denom;
        }

        switch(ctx->limitType) {
        case MatLMVM_Limit_Average:
          if (1.0 == ctx->mu) {
            ctx->sigma = sigmanew;
          } else if (ctx->mu) {
            ctx->sigma = ctx->mu * sigmanew + (1.0 - ctx->mu) * ctx->sigma;
          }
          break;

        case MatLMVM_Limit_Relative:
          if (ctx->mu) {
            ctx->sigma = TaoMid((1.0 - ctx->mu) * ctx->sigma, sigmanew, (1.0 + ctx->mu) * ctx->sigma);
          }
          break;

        case MatLMVM_Limit_Absolute:
          if (ctx->nu) {
            ctx->sigma = TaoMid(ctx->sigma - ctx->nu, sigmanew, ctx->sigma + ctx->nu);
          }
          break;

        default:
          ctx->sigma = sigmanew;
          break;
        }
        break;

      case MatLMVM_Scale_Broyden:
        /*  Original version */
        /*  Combine DFP and BFGS */

        /*  This code appears to be numerically unstable.  We use the */
        /*  original version because this was used to generate all of */
        /*  the data and because it may be the least unstable of the */
        /*  bunch. */

        /*  P = Q = inv(D); */
        ierr = VecCopy(ctx->D,ctx->P);CHKERRQ(ierr);
        ierr = VecReciprocal(ctx->P);CHKERRQ(ierr);
        ierr = VecCopy(ctx->P,ctx->Q);CHKERRQ(ierr);

        /*  V = y*y */
        ierr = VecPointwiseMult(ctx->V,ctx->Gprev,ctx->Gprev);CHKERRQ(ierr);

        /*  W = inv(D)*s */
        ierr = VecPointwiseMult(ctx->W,ctx->Xprev,ctx->P);CHKERRQ(ierr);
        ierr = VecDot(ctx->W,ctx->Xprev,&sDs);CHKERRQ(ierr);

        /*  Safeguard rhotemp and sDs */
        if (0.0 == rhotemp) {
          rhotemp = TAO_ZERO_SAFEGUARD;
        }

        if (0.0 == sDs) {
          sDs = TAO_ZERO_SAFEGUARD;
        }

        if (1.0 != ctx->phi) {
          /*  BFGS portion of the update */
          /*  U = (inv(D)*s)*(inv(D)*s) */
          ierr = VecPointwiseMult(ctx->U,ctx->W,ctx->W);CHKERRQ(ierr);

          /*  Assemble */
          ierr = VecAXPY(ctx->P,1.0/rhotemp,ctx->V);CHKERRQ(ierr);
          ierr = VecAXPY(ctx->P,-1.0/sDs,ctx->U);CHKERRQ(ierr);
        }

        if (0.0 != ctx->phi) {
          /*  DFP portion of the update */
          /*  U = inv(D)*s*y */
          ierr = VecPointwiseMult(ctx->U, ctx->W, ctx->Gprev);CHKERRQ(ierr);

          /*  Assemble */
          ierr = VecAXPY(ctx->Q,1.0/rhotemp + sDs/(rhotemp*rhotemp), ctx->V);CHKERRQ(ierr);
          ierr = VecAXPY(ctx->Q,-2.0/rhotemp,ctx->U);CHKERRQ(ierr);
        }

        if (0.0 == ctx->phi) {
            ierr = VecCopy(ctx->P,ctx->U);CHKERRQ(ierr);
        } else if (1.0 == ctx->phi) {
            ierr = VecCopy(ctx->Q,ctx->U);CHKERRQ(ierr);
        } else {
          /*  Broyden update U=(1-phi)*P + phi*Q */
            ierr = VecCopy(ctx->Q,ctx->U);CHKERRQ(ierr);
            ierr = VecAXPBY(ctx->U,1.0-ctx->phi, ctx->phi, ctx->P);CHKERRQ(ierr);
        }

        /*  Obtain inverse and ensure positive definite */
        ierr = VecReciprocal(ctx->U);CHKERRQ(ierr);
        ierr = VecAbs(ctx->U);CHKERRQ(ierr);

        switch(ctx->rScaleType) {
        case MatLMVM_Rescale_None:
            break;

        case MatLMVM_Rescale_Scalar:
        case MatLMVM_Rescale_GL:
          if (ctx->rScaleType == MatLMVM_Rescale_GL) {
            /*  Gilbert and Lemarachal use the old diagonal */
            ierr = VecCopy(ctx->D,ctx->P);CHKERRQ(ierr);
          } else {
            /*  The default version uses the current diagonal */
              ierr = VecCopy(ctx->U,ctx->P);CHKERRQ(ierr);
          }

          /*  Compute s^T s  */
          ierr = VecDot(ctx->Xprev,ctx->Xprev,&s0temp);CHKERRQ(ierr);

          /*  Save information for special cases of scalar rescaling */
          ctx->yy_rhistory[(ctx->nupdates - 1) % ctx->rescale_history] = y0temp;
          ctx->ys_rhistory[(ctx->nupdates - 1) % ctx->rescale_history] = rhotemp;
          ctx->ss_rhistory[(ctx->nupdates - 1) % ctx->rescale_history] = s0temp;

          if (0.5 == ctx->r_beta) {
            if (1 == PetscMin(ctx->nupdates, ctx->rescale_history)) {
              ierr = VecPointwiseMult(ctx->V,ctx->Y[0],ctx->P);CHKERRQ(ierr);
              ierr = VecDot(ctx->V,ctx->Y[0],&yy_sum);CHKERRQ(ierr);

              ierr = VecPointwiseDivide(ctx->W,ctx->S[0],ctx->P);CHKERRQ(ierr);
              ierr = VecDot(ctx->W,ctx->S[0],&ss_sum);CHKERRQ(ierr);

              ys_sum = ctx->ys_rhistory[0];
            } else {
              ierr = VecCopy(ctx->P,ctx->Q);CHKERRQ(ierr);
              ierr = VecReciprocal(ctx->Q);CHKERRQ(ierr);

              /*  Compute summations for scalar scaling */
              yy_sum = 0;       /*  No safeguard required */
              ys_sum = 0;       /*  No safeguard required */
              ss_sum = 0;       /*  No safeguard required */
              for (i = 0; i < PetscMin(ctx->nupdates, ctx->rescale_history); ++i) {
                ierr = VecPointwiseMult(ctx->V,ctx->Y[i],ctx->P);CHKERRQ(ierr);
                ierr = VecDot(ctx->V,ctx->Y[i],&yDy);CHKERRQ(ierr);
                yy_sum += yDy;

                ierr = VecPointwiseMult(ctx->W,ctx->S[i],ctx->Q);CHKERRQ(ierr);
                ierr = VecDot(ctx->W,ctx->S[i],&sDs);CHKERRQ(ierr);
                ss_sum += sDs;
                ys_sum += ctx->ys_rhistory[i];
              }
            }
          } else if (0.0 == ctx->r_beta) {
            if (1 == PetscMin(ctx->nupdates, ctx->rescale_history)) {
              /*  Compute summations for scalar scaling */
              ierr = VecPointwiseDivide(ctx->W,ctx->S[0],ctx->P);CHKERRQ(ierr);

              ierr = VecDot(ctx->W, ctx->Y[0], &ys_sum);CHKERRQ(ierr);
              ierr = VecDot(ctx->W, ctx->W, &ss_sum);CHKERRQ(ierr);
              yy_sum += ctx->yy_rhistory[0];
            } else {
              ierr = VecCopy(ctx->Q, ctx->P);CHKERRQ(ierr);
              ierr = VecReciprocal(ctx->Q);CHKERRQ(ierr);

              /*  Compute summations for scalar scaling */
              yy_sum = 0;       /*  No safeguard required */
              ys_sum = 0;       /*  No safeguard required */
              ss_sum = 0;       /*  No safeguard required */
              for (i = 0; i < PetscMin(ctx->nupdates, ctx->rescale_history); ++i) {
                ierr = VecPointwiseMult(ctx->W, ctx->S[i], ctx->Q);CHKERRQ(ierr);
                ierr = VecDot(ctx->W, ctx->Y[i], &yDs);CHKERRQ(ierr);
                ys_sum += yDs;

                ierr = VecDot(ctx->W, ctx->W, &sDs);CHKERRQ(ierr);
                ss_sum += sDs;

                yy_sum += ctx->yy_rhistory[i];
              }
            }
          } else if (1.0 == ctx->r_beta) {
            /*  Compute summations for scalar scaling */
            yy_sum = 0; /*  No safeguard required */
            ys_sum = 0; /*  No safeguard required */
            ss_sum = 0; /*  No safeguard required */
            for (i = 0; i < PetscMin(ctx->nupdates, ctx->rescale_history); ++i) {
              ierr = VecPointwiseMult(ctx->V, ctx->Y[i], ctx->P);CHKERRQ(ierr);
              ierr = VecDot(ctx->V, ctx->S[i], &yDs);CHKERRQ(ierr);
              ys_sum += yDs;

              ierr = VecDot(ctx->V, ctx->V, &yDy);CHKERRQ(ierr);
              yy_sum += yDy;

              ss_sum += ctx->ss_rhistory[i];
            }
          } else {
            ierr = VecCopy(ctx->Q, ctx->P);CHKERRQ(ierr);

            ierr = VecPow(ctx->P, ctx->r_beta);CHKERRQ(ierr);
            ierr = VecPointwiseDivide(ctx->Q, ctx->P, ctx->Q);CHKERRQ(ierr);

            /*  Compute summations for scalar scaling */
            yy_sum = 0; /*  No safeguard required */
            ys_sum = 0; /*  No safeguard required */
            ss_sum = 0; /*  No safeguard required */
            for (i = 0; i < PetscMin(ctx->nupdates, ctx->rescale_history); ++i) {
              ierr = VecPointwiseMult(ctx->V, ctx->P, ctx->Y[i]);CHKERRQ(ierr);
              ierr = VecPointwiseMult(ctx->W, ctx->Q, ctx->S[i]);CHKERRQ(ierr);

              ierr = VecDot(ctx->V, ctx->V, &yDy);CHKERRQ(ierr);
              ierr = VecDot(ctx->V, ctx->W, &yDs);CHKERRQ(ierr);
              ierr = VecDot(ctx->W, ctx->W, &sDs);CHKERRQ(ierr);

              yy_sum += yDy;
              ys_sum += yDs;
              ss_sum += sDs;
            }
          }

          if (0.0 == ctx->r_alpha) {
            /*  Safeguard ys_sum  */
            if (0.0 == ys_sum) {
              ys_sum = TAO_ZERO_SAFEGUARD;
            }

            sigmanew = ss_sum / ys_sum;
          } else if (1.0 == ctx->r_alpha) {
            /*  Safeguard yy_sum  */
            if (0.0 == yy_sum) {
              ys_sum = TAO_ZERO_SAFEGUARD;
            }

            sigmanew = ys_sum / yy_sum;
          } else {
            denom = 2*ctx->r_alpha*yy_sum;

            /*  Safeguard denom */
            if (0.0 == denom) {
              denom = TAO_ZERO_SAFEGUARD;
            }

            sigmanew = ((2*ctx->r_alpha-1)*ys_sum + PetscSqrtScalar((2*ctx->r_alpha-1)*(2*ctx->r_alpha-1)*ys_sum*ys_sum - 4*ctx->r_alpha*(ctx->r_alpha-1)*yy_sum*ss_sum)) / denom;
          }

          /*  If Q has small values, then Q^(r_beta - 1) */
          /*  can have very large values.  Hence, ys_sum */
          /*  and ss_sum can be infinity.  In this case, */
          /*  sigmanew can either be not-a-number or infinity. */

          if (PetscIsInfOrNanReal(sigmanew)) {
            /*  sigmanew is not-a-number; skip rescaling */
          } else if (!sigmanew) {
            /*  sigmanew is zero; this is a bad case; skip rescaling */
          } else {
            /*  sigmanew is positive */
            ierr = VecScale(ctx->U, sigmanew);CHKERRQ(ierr);
          }
          break;
        }

        /*  Modify for previous information */
        switch(ctx->limitType) {
        case MatLMVM_Limit_Average:
          if (1.0 == ctx->mu) {
            ierr = VecCopy(ctx->D, ctx->U);CHKERRQ(ierr);
          } else if (ctx->mu) {
            ierr = VecAXPBY(ctx->D,ctx->mu, 1.0-ctx->mu,ctx->U);CHKERRQ(ierr);
          }
          break;

        case MatLMVM_Limit_Relative:
          if (ctx->mu) {
            /*  P = (1-mu) * D */
            ierr = VecAXPBY(ctx->P, 1.0-ctx->mu, 0.0, ctx->D);CHKERRQ(ierr);
            /*  Q = (1+mu) * D */
            ierr = VecAXPBY(ctx->Q, 1.0+ctx->mu, 0.0, ctx->D);CHKERRQ(ierr);
            ierr = VecMedian(ctx->P, ctx->U, ctx->Q, ctx->D);CHKERRQ(ierr);
          }
          break;

        case MatLMVM_Limit_Absolute:
          if (ctx->nu) {
            ierr = VecCopy(ctx->P, ctx->D);CHKERRQ(ierr);
            ierr = VecShift(ctx->P, -ctx->nu);CHKERRQ(ierr);
            ierr = VecCopy(ctx->D, ctx->Q);CHKERRQ(ierr);
            ierr = VecShift(ctx->Q, ctx->nu);CHKERRQ(ierr);
            ierr = VecMedian(ctx->P, ctx->U, ctx->Q, ctx->P);CHKERRQ(ierr);
          }
          break;

        default:
            ierr = VecCopy(ctx->U, ctx->D);CHKERRQ(ierr);
          break;
        }
        break;
      }
      ierr = PetscObjectDereference((PetscObject)ctx->Xprev);CHKERRQ(ierr);
      ierr = PetscObjectDereference((PetscObject)ctx->Gprev);CHKERRQ(ierr);
      ctx->Xprev = ctx->S[ctx->lm];
      ctx->Gprev = ctx->Y[ctx->lm];
      ierr = PetscObjectReference((PetscObject)ctx->S[ctx->lm]);CHKERRQ(ierr);
      ierr = PetscObjectReference((PetscObject)ctx->Y[ctx->lm]);CHKERRQ(ierr);

    } else {
      ++ctx->nrejects;
    }
  }

  ++ctx->iter;
  ierr = VecCopy(x, ctx->Xprev);CHKERRQ(ierr);
  ierr = VecCopy(g, ctx->Gprev);CHKERRQ(ierr);
  PetscFunctionReturn(0);
}
コード例 #6
0
ファイル: blmvm.c プロジェクト: masa-ito/PETScToPoisson
static PetscErrorCode TaoSolve_BLMVM(Tao tao)
{
  PetscErrorCode               ierr;
  TAO_BLMVM                    *blmP = (TAO_BLMVM *)tao->data;
  TaoConvergedReason           reason = TAO_CONTINUE_ITERATING;
  TaoLineSearchConvergedReason ls_status = TAOLINESEARCH_CONTINUE_ITERATING;
  PetscReal                    f, fold, gdx, gnorm;
  PetscReal                    stepsize = 1.0,delta;

  PetscFunctionBegin;
  /*  Project initial point onto bounds */
  ierr = TaoComputeVariableBounds(tao);CHKERRQ(ierr);
  ierr = VecMedian(tao->XL,tao->solution,tao->XU,tao->solution);CHKERRQ(ierr);
  ierr = TaoLineSearchSetVariableBounds(tao->linesearch,tao->XL,tao->XU);CHKERRQ(ierr);


  /* Check convergence criteria */
  ierr = TaoComputeObjectiveAndGradient(tao, tao->solution,&f,blmP->unprojected_gradient);CHKERRQ(ierr);
  ierr = VecBoundGradientProjection(blmP->unprojected_gradient,tao->solution, tao->XL,tao->XU,tao->gradient);CHKERRQ(ierr);

  ierr = TaoGradientNorm(tao, tao->gradient,NORM_2,&gnorm);CHKERRQ(ierr);
  if (PetscIsInfOrNanReal(f) || PetscIsInfOrNanReal(gnorm)) SETERRQ(PETSC_COMM_SELF,1, "User provided compute function generated Inf pr NaN");

  ierr = TaoMonitor(tao, tao->niter, f, gnorm, 0.0, stepsize, &reason);CHKERRQ(ierr);
  if (reason != TAO_CONTINUE_ITERATING) PetscFunctionReturn(0);

  /* Set initial scaling for the function */
  if (f != 0.0) {
    delta = 2.0*PetscAbsScalar(f) / (gnorm*gnorm);
  } else {
    delta = 2.0 / (gnorm*gnorm);
  }
  ierr = MatLMVMSetDelta(blmP->M,delta);CHKERRQ(ierr);

  /* Set counter for gradient/reset steps */
  blmP->grad = 0;
  blmP->reset = 0;

  /* Have not converged; continue with Newton method */
  while (reason == TAO_CONTINUE_ITERATING) {
    /* Compute direction */
    ierr = MatLMVMUpdate(blmP->M, tao->solution, tao->gradient);CHKERRQ(ierr);
    ierr = MatLMVMSolve(blmP->M, blmP->unprojected_gradient, tao->stepdirection);CHKERRQ(ierr);
    ierr = VecBoundGradientProjection(tao->stepdirection,tao->solution,tao->XL,tao->XU,tao->gradient);CHKERRQ(ierr);

    /* Check for success (descent direction) */
    ierr = VecDot(blmP->unprojected_gradient, tao->gradient, &gdx);CHKERRQ(ierr);
    if (gdx <= 0) {
      /* Step is not descent or solve was not successful
         Use steepest descent direction (scaled) */
      ++blmP->grad;

      if (f != 0.0) {
        delta = 2.0*PetscAbsScalar(f) / (gnorm*gnorm);
      } else {
        delta = 2.0 / (gnorm*gnorm);
      }
      ierr = MatLMVMSetDelta(blmP->M,delta);CHKERRQ(ierr);
      ierr = MatLMVMReset(blmP->M);CHKERRQ(ierr);
      ierr = MatLMVMUpdate(blmP->M, tao->solution, blmP->unprojected_gradient);CHKERRQ(ierr);
      ierr = MatLMVMSolve(blmP->M,blmP->unprojected_gradient, tao->stepdirection);CHKERRQ(ierr);
    }
    ierr = VecScale(tao->stepdirection,-1.0);CHKERRQ(ierr);

    /* Perform the linesearch */
    fold = f;
    ierr = VecCopy(tao->solution, blmP->Xold);CHKERRQ(ierr);
    ierr = VecCopy(blmP->unprojected_gradient, blmP->Gold);CHKERRQ(ierr);
    ierr = TaoLineSearchSetInitialStepLength(tao->linesearch,1.0);CHKERRQ(ierr);
    ierr = TaoLineSearchApply(tao->linesearch, tao->solution, &f, blmP->unprojected_gradient, tao->stepdirection, &stepsize, &ls_status);CHKERRQ(ierr);
    ierr = TaoAddLineSearchCounts(tao);CHKERRQ(ierr);

    if (ls_status != TAOLINESEARCH_SUCCESS && ls_status != TAOLINESEARCH_SUCCESS_USER) {
      /* Linesearch failed
         Reset factors and use scaled (projected) gradient step */
      ++blmP->reset;

      f = fold;
      ierr = VecCopy(blmP->Xold, tao->solution);CHKERRQ(ierr);
      ierr = VecCopy(blmP->Gold, blmP->unprojected_gradient);CHKERRQ(ierr);

      if (f != 0.0) {
        delta = 2.0* PetscAbsScalar(f) / (gnorm*gnorm);
      } else {
        delta = 2.0/ (gnorm*gnorm);
      }
      ierr = MatLMVMSetDelta(blmP->M,delta);CHKERRQ(ierr);
      ierr = MatLMVMReset(blmP->M);CHKERRQ(ierr);
      ierr = MatLMVMUpdate(blmP->M, tao->solution, blmP->unprojected_gradient);CHKERRQ(ierr);
      ierr = MatLMVMSolve(blmP->M, blmP->unprojected_gradient, tao->stepdirection);CHKERRQ(ierr);
      ierr = VecScale(tao->stepdirection, -1.0);CHKERRQ(ierr);

      /* This may be incorrect; linesearch has values fo stepmax and stepmin
         that should be reset. */
      ierr = TaoLineSearchSetInitialStepLength(tao->linesearch,1.0);CHKERRQ(ierr);
      ierr = TaoLineSearchApply(tao->linesearch,tao->solution,&f, blmP->unprojected_gradient, tao->stepdirection,  &stepsize, &ls_status);CHKERRQ(ierr);
      ierr = TaoAddLineSearchCounts(tao);CHKERRQ(ierr);

      if (ls_status != TAOLINESEARCH_SUCCESS && ls_status != TAOLINESEARCH_SUCCESS_USER) {
        tao->reason = TAO_DIVERGED_LS_FAILURE;
        break;
      }
    }

    /* Check for converged */
    ierr = VecBoundGradientProjection(blmP->unprojected_gradient, tao->solution, tao->XL, tao->XU, tao->gradient);CHKERRQ(ierr);
    ierr = TaoGradientNorm(tao, tao->gradient, NORM_2, &gnorm);CHKERRQ(ierr);


    if (PetscIsInfOrNanReal(f) || PetscIsInfOrNanReal(gnorm)) SETERRQ(PETSC_COMM_SELF,1, "User provided compute function generated Not-a-Number");
    tao->niter++;
    ierr = TaoMonitor(tao, tao->niter, f, gnorm, 0.0, stepsize, &reason);CHKERRQ(ierr);
  }
  PetscFunctionReturn(0);
}