Example #1
0
/* Returns step length which gives minimum of objective for
   solution + theta * change vector up to maximum theta.

   arrays are numberColumns+numberRows
*/
double
ClpAmplObjective::stepLength(ClpSimplex * model,
                             const double * solution,
                             const double * change,
                             double maximumTheta,
                             double & currentObj,
                             double & predictedObj,
                             double & thetaObj)
{
    // Assume convex
    CbcAmplInfo * info = (CbcAmplInfo *) amplObjective_;
    ASL_pfgh* asl = info->asl_;

    int numberColumns = n_var;;
    double * tempSolution = new double [numberColumns];
    double * tempGradient = new double [numberColumns];
    // current
    eval_f(amplObjective_, numberColumns, solution, true, currentObj);
    double objA = currentObj;
    double thetaA = 0.0;
    // at maximum
    int i;
    for (i = 0; i < numberColumns; i++)
        tempSolution[i] = solution[i] + maximumTheta * change[i];
    eval_f(amplObjective_, numberColumns, tempSolution, true, thetaObj);
    double objC = thetaObj;
    double thetaC = maximumTheta;
    double objB = 0.5 * (objA + objC);
    double thetaB = 0.5 * maximumTheta;
    double gradientNorm = 1.0e6;
    while (gradientNorm > 1.0e-6 && thetaC - thetaA > 1.0e-8) {
        for (i = 0; i < numberColumns; i++)
            tempSolution[i] = solution[i] + thetaB * change[i];
        eval_grad_f(amplObjective_, numberColumns, tempSolution, true, tempGradient);
        eval_f(amplObjective_, numberColumns, tempSolution, false, objB);
        double changeObj = 0.0;
        gradientNorm = 0.0;
        for (i = 0; i < numberColumns; i++) {
            changeObj += tempGradient[i] * change[i];
            gradientNorm += tempGradient[i] * tempGradient[i];
        }
        gradientNorm = fabs(changeObj) / sqrt(gradientNorm);
        // Should try and get quadratic convergence by interpolation
        if (changeObj < 0.0) {
            // increasing is good
            thetaA = thetaB;
        } else {
            // decreasing is good
            thetaC = thetaB;
        }
        thetaB = 0.5 * (thetaA + thetaC);
    }
    delete [] tempSolution;
    delete [] tempGradient;
    predictedObj = objB;
    return thetaB;
}
Example #2
0
// Returns gradient
double *
ClpAmplObjective::gradient(const ClpSimplex * model,
                           const double * solution, double & offset, bool refresh,
                           int includeLinear)
{
    if (model)
        assert (model->optimizationDirection() == 1.0);
#ifndef NDEBUG
    bool scaling = model && (model->rowScale() || model->objectiveScale() != 1.0 || model->optimizationDirection() != 1.0);
#endif
    const double * cost = NULL;
    if (model)
        cost = model->costRegion();
    if (!cost) {
        // not in solve
        cost = objective_;
#ifndef NDEBUG
        scaling = false;
#endif
    }
    assert (!scaling);
    if (!amplObjective_ || !solution || !activated_) {
        offset = offset_;
        return objective_;
    } else {
        if (refresh || !gradient_) {
            CbcAmplInfo * info = (CbcAmplInfo *) amplObjective_;
            ASL_pfgh* asl = info->asl_;
            int numberColumns = n_var;;

            if (!gradient_)
                gradient_ = new double[numberColumns];
            assert (solution);
            eval_grad_f(amplObjective_, numberColumns, solution, true, gradient_);
            // Is this best way?
            double objValue = 0.0;
            eval_f(amplObjective_, numberColumns, solution, false, objValue);
            double objValue2 = 0.0;
            for (int i = 0; i < numberColumns; i++)
                objValue2 += gradient_[i] * solution[i];
            offset_ = objValue2 - objValue; // or other way???
            if (model && model->optimizationDirection() != 1.0) {
                offset *= model->optimizationDirection();
                for (int i = 0; i < numberColumns; i++)
                    gradient_[i] *= -1.0;
            }
        }
        offset = offset_;
        return gradient_;
    }
}
Example #3
0
  /** This methods gives the linear part of the objective function */
  void AmplTMINLP::getLinearPartOfObjective(double * obj)
  {
    Index n, m, nnz_jac_g, nnz_h_lag;
    TNLP::IndexStyleEnum index_style = TNLP::FORTRAN_STYLE;
    get_nlp_info( n, m, nnz_jac_g, nnz_h_lag, index_style);
    eval_grad_f(n, NULL, 0,obj);
    Index n_non_linear_b= 0;
    Index n_non_linear_bi= 0;
    Index n_non_linear_c= 0;
    Index n_non_linear_ci = 0;
    Index n_non_linear_o= 0;
    Index n_non_linear_oi = 0;
    Index n_binaries = 0;
    Index n_integers = 0;
    ampl_tnlp_->get_discrete_info(n_non_linear_b, n_non_linear_bi, n_non_linear_c,
        n_non_linear_ci, n_non_linear_o, n_non_linear_oi,
        n_binaries, n_integers);

    // Now get the coefficients of variables wich are linear in the objective
    // The first ones are not
    Index start = 0;
    Index end = n_non_linear_b;
    for (int i=start; i<end; i++) {
      obj[i] = 0.;
    }

    //next variables should be linear in the objective just skip them
    // (from current end to (end + n_non_linear_c - n_non_linear_ci - n_non_linear_b;)


    // Those are nonlinear in the objective
    start = end + n_non_linear_c;
    end = start + n_non_linear_o;
    for (int i=start; i < end; i++) {
      obj[i]=0.;
    }
    //The rest is linear keep the values of the gradient
  }
Example #4
0
  void Sqpmethod::evaluate() {
    if (inputs_check_) checkInputs();
    checkInitialBounds();

    if (gather_stats_) {
      Dict iterations;
      iterations["inf_pr"] = std::vector<double>();
      iterations["inf_du"] = std::vector<double>();
      iterations["ls_trials"] = std::vector<double>();
      iterations["d_norm"] = std::vector<double>();
      iterations["obj"] = std::vector<double>();
      stats_["iterations"] = iterations;
    }


    // Get problem data
    const vector<double>& x_init = input(NLP_SOLVER_X0).data();
    const vector<double>& lbx = input(NLP_SOLVER_LBX).data();
    const vector<double>& ubx = input(NLP_SOLVER_UBX).data();
    const vector<double>& lbg = input(NLP_SOLVER_LBG).data();
    const vector<double>& ubg = input(NLP_SOLVER_UBG).data();

    // Set linearization point to initial guess
    copy(x_init.begin(), x_init.end(), x_.begin());

    // Initialize Lagrange multipliers of the NLP
    copy(input(NLP_SOLVER_LAM_G0).begin(), input(NLP_SOLVER_LAM_G0).end(), mu_.begin());
    copy(input(NLP_SOLVER_LAM_X0).begin(), input(NLP_SOLVER_LAM_X0).end(), mu_x_.begin());

    t_eval_f_ = t_eval_grad_f_ = t_eval_g_ = t_eval_jac_g_ = t_eval_h_ =
        t_callback_fun_ = t_callback_prepare_ = t_mainloop_ = 0;

    n_eval_f_ = n_eval_grad_f_ = n_eval_g_ = n_eval_jac_g_ = n_eval_h_ = 0;

    double time1 = clock();

    // Initial constraint Jacobian
    eval_jac_g(x_, gk_, Jk_);

    // Initial objective gradient
    eval_grad_f(x_, fk_, gf_);

    // Initialize or reset the Hessian or Hessian approximation
    reg_ = 0;
    if (exact_hessian_) {
      eval_h(x_, mu_, 1.0, Bk_);
    } else {
      reset_h();
    }

    // Evaluate the initial gradient of the Lagrangian
    copy(gf_.begin(), gf_.end(), gLag_.begin());
    if (ng_>0) casadi_mv_t(Jk_.ptr(), Jk_.sparsity(), getPtr(mu_), getPtr(gLag_));
    // gLag += mu_x_;
    transform(gLag_.begin(), gLag_.end(), mu_x_.begin(), gLag_.begin(), plus<double>());

    // Number of SQP iterations
    int iter = 0;

    // Number of line-search iterations
    int ls_iter = 0;

    // Last linesearch successfull
    bool ls_success = true;

    // Reset
    merit_mem_.clear();
    sigma_ = 0.;    // NOTE: Move this into the main optimization loop

    // Default stepsize
    double t = 0;

    // MAIN OPTIMIZATION LOOP
    while (true) {

      // Primal infeasability
      double pr_inf = primalInfeasibility(x_, lbx, ubx, gk_, lbg, ubg);

      // inf-norm of lagrange gradient
      double gLag_norminf = norm_inf(gLag_);

      // inf-norm of step
      double dx_norminf = norm_inf(dx_);

      // Print header occasionally
      if (iter % 10 == 0) printIteration(userOut());

      // Printing information about the actual iterate
      printIteration(userOut(), iter, fk_, pr_inf, gLag_norminf, dx_norminf,
                     reg_, ls_iter, ls_success);

      if (gather_stats_) {
        Dict iterations = stats_["iterations"];
        std::vector<double> tmp=iterations["inf_pr"];
        tmp.push_back(pr_inf);
        iterations["inf_pr"] = tmp;

        tmp=iterations["inf_du"];
        tmp.push_back(gLag_norminf);
        iterations["inf_du"] = tmp;

        tmp=iterations["d_norm"];
        tmp.push_back(dx_norminf);
        iterations["d_norm"] = tmp;

        std::vector<int> tmp2=iterations["ls_trials"];
        tmp2.push_back(ls_iter);
        iterations["ls_trials"] = tmp2;

        tmp=iterations["obj"];
        tmp.push_back(fk_);
        iterations["obj"] = tmp;

        stats_["iterations"] = iterations;
      }

      // Call callback function if present
      if (!callback_.isNull()) {
        double time1 = clock();

        if (!output(NLP_SOLVER_F).isempty()) output(NLP_SOLVER_F).set(fk_);
        if (!output(NLP_SOLVER_X).isempty()) output(NLP_SOLVER_X).setNZ(x_);
        if (!output(NLP_SOLVER_LAM_G).isempty()) output(NLP_SOLVER_LAM_G).setNZ(mu_);
        if (!output(NLP_SOLVER_LAM_X).isempty()) output(NLP_SOLVER_LAM_X).setNZ(mu_x_);
        if (!output(NLP_SOLVER_G).isempty()) output(NLP_SOLVER_G).setNZ(gk_);

        Dict iteration;
        iteration["iter"] = iter;
        iteration["inf_pr"] = pr_inf;
        iteration["inf_du"] = gLag_norminf;
        iteration["d_norm"] = dx_norminf;
        iteration["ls_trials"] = ls_iter;
        iteration["obj"] = fk_;
        stats_["iteration"] = iteration;

        double time2 = clock();
        t_callback_prepare_ += (time2-time1)/CLOCKS_PER_SEC;
        time1 = clock();
        int ret = callback_(ref_, user_data_);
        time2 = clock();
        t_callback_fun_ += (time2-time1)/CLOCKS_PER_SEC;
        if (ret) {
          userOut() << endl;
          userOut() << "casadi::SQPMethod: aborted by callback..." << endl;
          stats_["return_status"] = "User_Requested_Stop";
          break;
        }
      }

      // Checking convergence criteria
      if (pr_inf < tol_pr_ && gLag_norminf < tol_du_) {
        userOut() << endl;
        userOut() << "casadi::SQPMethod: Convergence achieved after "
                  << iter << " iterations." << endl;
        stats_["return_status"] = "Solve_Succeeded";
        break;
      }

      if (iter >= max_iter_) {
        userOut() << endl;
        userOut() << "casadi::SQPMethod: Maximum number of iterations reached." << endl;
        stats_["return_status"] = "Maximum_Iterations_Exceeded";
        break;
      }

      if (iter > 0 && dx_norminf <= min_step_size_) {
        userOut() << endl;
        userOut() << "casadi::SQPMethod: Search direction becomes too small without "
            "convergence criteria being met." << endl;
        stats_["return_status"] = "Search_Direction_Becomes_Too_Small";
        break;
      }

      // Start a new iteration
      iter++;

      log("Formulating QP");
      // Formulate the QP
      transform(lbx.begin(), lbx.end(), x_.begin(), qp_LBX_.begin(), minus<double>());
      transform(ubx.begin(), ubx.end(), x_.begin(), qp_UBX_.begin(), minus<double>());
      transform(lbg.begin(), lbg.end(), gk_.begin(), qp_LBA_.begin(), minus<double>());
      transform(ubg.begin(), ubg.end(), gk_.begin(), qp_UBA_.begin(), minus<double>());

      // Solve the QP
      solve_QP(Bk_, gf_, qp_LBX_, qp_UBX_, Jk_, qp_LBA_, qp_UBA_, dx_, qp_DUAL_X_, qp_DUAL_A_);
      log("QP solved");

      // Detecting indefiniteness
      double gain = casadi_quad_form(Bk_.ptr(), Bk_.sparsity(), getPtr(dx_));
      if (gain < 0) {
        casadi_warning("Indefinite Hessian detected...");
      }

      // Calculate penalty parameter of merit function
      sigma_ = std::max(sigma_, 1.01*norm_inf(qp_DUAL_X_));
      sigma_ = std::max(sigma_, 1.01*norm_inf(qp_DUAL_A_));

      // Calculate L1-merit function in the actual iterate
      double l1_infeas = primalInfeasibility(x_, lbx, ubx, gk_, lbg, ubg);

      // Right-hand side of Armijo condition
      double F_sens = inner_prod(dx_, gf_);
      double L1dir = F_sens - sigma_ * l1_infeas;
      double L1merit = fk_ + sigma_ * l1_infeas;

      // Storing the actual merit function value in a list
      merit_mem_.push_back(L1merit);
      if (merit_mem_.size() > merit_memsize_) {
        merit_mem_.pop_front();
      }
      // Stepsize
      t = 1.0;
      double fk_cand;
      // Merit function value in candidate
      double L1merit_cand = 0;

      // Reset line-search counter, success marker
      ls_iter = 0;
      ls_success = true;

      // Line-search
      log("Starting line-search");
      if (max_iter_ls_>0) { // max_iter_ls_== 0 disables line-search

        // Line-search loop
        while (true) {
          for (int i=0; i<nx_; ++i) x_cand_[i] = x_[i] + t * dx_[i];

          try {
            // Evaluating objective and constraints
            eval_f(x_cand_, fk_cand);
            eval_g(x_cand_, gk_cand_);
          } catch(const CasadiException& ex) {
            // Silent ignore; line-search failed
            ls_iter++;
            // Backtracking
            t = beta_ * t;
            continue;
          }

          ls_iter++;

          // Calculating merit-function in candidate
          l1_infeas = primalInfeasibility(x_cand_, lbx, ubx, gk_cand_, lbg, ubg);

          L1merit_cand = fk_cand + sigma_ * l1_infeas;
          // Calculating maximal merit function value so far
          double meritmax = *max_element(merit_mem_.begin(), merit_mem_.end());
          if (L1merit_cand <= meritmax + t * c1_ * L1dir) {
            // Accepting candidate
            log("Line-search completed, candidate accepted");
            break;
          }

          // Line-search not successful, but we accept it.
          if (ls_iter == max_iter_ls_) {
            ls_success = false;
            log("Line-search completed, maximum number of iterations");
            break;
          }

          // Backtracking
          t = beta_ * t;
        }

        // Candidate accepted, update dual variables
        for (int i=0; i<ng_; ++i) mu_[i] = t * qp_DUAL_A_[i] + (1 - t) * mu_[i];
        for (int i=0; i<nx_; ++i) mu_x_[i] = t * qp_DUAL_X_[i] + (1 - t) * mu_x_[i];

        // Candidate accepted, update the primal variable
        copy(x_.begin(), x_.end(), x_old_.begin());
        copy(x_cand_.begin(), x_cand_.end(), x_.begin());

      } else {
        // Full step
        copy(qp_DUAL_A_.begin(), qp_DUAL_A_.end(), mu_.begin());
        copy(qp_DUAL_X_.begin(), qp_DUAL_X_.end(), mu_x_.begin());

        copy(x_.begin(), x_.end(), x_old_.begin());
        // x+=dx
        transform(x_.begin(), x_.end(), dx_.begin(), x_.begin(), plus<double>());
      }

      if (!exact_hessian_) {
        // Evaluate the gradient of the Lagrangian with the old x but new mu (for BFGS)
        copy(gf_.begin(), gf_.end(), gLag_old_.begin());
        if (ng_>0) casadi_mv_t(Jk_.ptr(), Jk_.sparsity(), getPtr(mu_), getPtr(gLag_old_));
        // gLag_old += mu_x_;
        transform(gLag_old_.begin(), gLag_old_.end(), mu_x_.begin(), gLag_old_.begin(),
                  plus<double>());
      }

      // Evaluate the constraint Jacobian
      log("Evaluating jac_g");
      eval_jac_g(x_, gk_, Jk_);

      // Evaluate the gradient of the objective function
      log("Evaluating grad_f");
      eval_grad_f(x_, fk_, gf_);

      // Evaluate the gradient of the Lagrangian with the new x and new mu
      copy(gf_.begin(), gf_.end(), gLag_.begin());
      if (ng_>0) casadi_mv_t(Jk_.ptr(), Jk_.sparsity(), getPtr(mu_), getPtr(gLag_));

      // gLag += mu_x_;
      transform(gLag_.begin(), gLag_.end(), mu_x_.begin(), gLag_.begin(), plus<double>());

      // Updating Lagrange Hessian
      if (!exact_hessian_) {
        log("Updating Hessian (BFGS)");
        // BFGS with careful updates and restarts
        if (iter % lbfgs_memory_ == 0) {
          // Reset Hessian approximation by dropping all off-diagonal entries
          const int* colind = Bk_.colind();      // Access sparsity (column offset)
          int ncol = Bk_.size2();
          const int* row = Bk_.row();            // Access sparsity (row)
          vector<double>& data = Bk_.data();             // Access nonzero elements
          for (int cc=0; cc<ncol; ++cc) {     // Loop over the columns of the Hessian
            for (int el=colind[cc]; el<colind[cc+1]; ++el) {
              // Loop over the nonzero elements of the column
              if (cc!=row[el]) data[el] = 0;               // Remove if off-diagonal entries
            }
          }
        }

        // Pass to BFGS update function
        bfgs_.setInput(Bk_, BFGS_BK);
        bfgs_.setInputNZ(x_, BFGS_X);
        bfgs_.setInputNZ(x_old_, BFGS_X_OLD);
        bfgs_.setInputNZ(gLag_, BFGS_GLAG);
        bfgs_.setInputNZ(gLag_old_, BFGS_GLAG_OLD);

        // Update the Hessian approximation
        bfgs_.evaluate();

        // Get the updated Hessian
        bfgs_.getOutput(Bk_);
        if (monitored("bfgs")) {
          userOut() << "x = " << x_ << endl;
          userOut() << "BFGS = "  << endl;
          Bk_.printSparse();
        }
      } else {
        // Exact Hessian
        log("Evaluating hessian");
        eval_h(x_, mu_, 1.0, Bk_);
      }
    }

    double time2 = clock();
    t_mainloop_ = (time2-time1)/CLOCKS_PER_SEC;

    // Save results to outputs
    output(NLP_SOLVER_F).set(fk_);
    output(NLP_SOLVER_X).setNZ(x_);
    output(NLP_SOLVER_LAM_G).setNZ(mu_);
    output(NLP_SOLVER_LAM_X).setNZ(mu_x_);
    output(NLP_SOLVER_G).setNZ(gk_);

    if (hasOption("print_time") && static_cast<bool>(getOption("print_time"))) {
      // Write timings
      userOut() << "time spent in eval_f: " << t_eval_f_ << " s.";
      if (n_eval_f_>0)
        userOut() << " (" << n_eval_f_ << " calls, " << (t_eval_f_/n_eval_f_)*1000
                  << " ms. average)";
      userOut() << endl;
      userOut() << "time spent in eval_grad_f: " << t_eval_grad_f_ << " s.";
      if (n_eval_grad_f_>0)
        userOut() << " (" << n_eval_grad_f_ << " calls, "
             << (t_eval_grad_f_/n_eval_grad_f_)*1000 << " ms. average)";
      userOut() << endl;
      userOut() << "time spent in eval_g: " << t_eval_g_ << " s.";
      if (n_eval_g_>0)
        userOut() << " (" << n_eval_g_ << " calls, " << (t_eval_g_/n_eval_g_)*1000
                  << " ms. average)";
      userOut() << endl;
      userOut() << "time spent in eval_jac_g: " << t_eval_jac_g_ << " s.";
      if (n_eval_jac_g_>0)
        userOut() << " (" << n_eval_jac_g_ << " calls, "
             << (t_eval_jac_g_/n_eval_jac_g_)*1000 << " ms. average)";
      userOut() << endl;
      userOut() << "time spent in eval_h: " << t_eval_h_ << " s.";
      if (n_eval_h_>1)
        userOut() << " (" << n_eval_h_ << " calls, " << (t_eval_h_/n_eval_h_)*1000
                  << " ms. average)";
      userOut() << endl;
      userOut() << "time spent in main loop: " << t_mainloop_ << " s." << endl;
      userOut() << "time spent in callback function: " << t_callback_fun_ << " s." << endl;
      userOut() << "time spent in callback preparation: " << t_callback_prepare_ << " s." << endl;
    }

    // Save statistics
    stats_["iter_count"] = iter;

    stats_["t_eval_f"] = t_eval_f_;
    stats_["t_eval_grad_f"] = t_eval_grad_f_;
    stats_["t_eval_g"] = t_eval_g_;
    stats_["t_eval_jac_g"] = t_eval_jac_g_;
    stats_["t_eval_h"] = t_eval_h_;
    stats_["t_mainloop"] = t_mainloop_;
    stats_["t_callback_fun"] = t_callback_fun_;
    stats_["t_callback_prepare"] = t_callback_prepare_;
    stats_["n_eval_f"] = n_eval_f_;
    stats_["n_eval_grad_f"] = n_eval_grad_f_;
    stats_["n_eval_g"] = n_eval_g_;
    stats_["n_eval_jac_g"] = n_eval_jac_g_;
    stats_["n_eval_h"] = n_eval_h_;
  }
Example #5
0
void SQPInternal::evaluate(int nfdir, int nadir){
  casadi_assert(nfdir==0 && nadir==0);
  
  checkInitialBounds();
  
  // Get problem data
  const vector<double>& x_init = input(NLP_X_INIT).data();
  const vector<double>& lbx = input(NLP_LBX).data();
  const vector<double>& ubx = input(NLP_UBX).data();
  const vector<double>& lbg = input(NLP_LBG).data();
  const vector<double>& ubg = input(NLP_UBG).data();
  
  // Set the static parameter
  if (parametric_) {
    const vector<double>& p = input(NLP_P).data();
    if (!F_.isNull()) F_.setInput(p,F_.getNumInputs()-1);
    if (!G_.isNull()) G_.setInput(p,G_.getNumInputs()-1);
    if (!H_.isNull()) H_.setInput(p,H_.getNumInputs()-1);
    if (!J_.isNull()) J_.setInput(p,J_.getNumInputs()-1);
  }
    
  // Set linearization point to initial guess
  copy(x_init.begin(),x_init.end(),x_.begin());
  
  // Lagrange multipliers of the NLP
  fill(mu_.begin(),mu_.end(),0);
  fill(mu_x_.begin(),mu_x_.end(),0);

  // Initial constraint Jacobian
  eval_jac_g(x_,gk_,Jk_);
  
  // Initial objective gradient
  eval_grad_f(x_,fk_,gf_);
  
  // Initialize or reset the Hessian or Hessian approximation
  reg_ = 0;
  if( hess_mode_ == HESS_BFGS){
    reset_h();
  } else {
    eval_h(x_,mu_,1.0,Bk_);
  }

  // Evaluate the initial gradient of the Lagrangian
  copy(gf_.begin(),gf_.end(),gLag_.begin());
  if(m_>0) DMatrix::mul_no_alloc_tn(Jk_,mu_,gLag_);
  // gLag += mu_x_;
  transform(gLag_.begin(),gLag_.end(),mu_x_.begin(),gLag_.begin(),plus<double>());

  // Number of SQP iterations
  int iter = 0;

  // Number of line-search iterations
  int ls_iter = 0;
  
  // Last linesearch successfull
  bool ls_success = true;
  
  // Reset
  merit_mem_.clear();
  sigma_ = 0.;    // NOTE: Move this into the main optimization loop

  // Default stepsize
  double t = 0;
  
  // MAIN OPTIMIZATION LOOP
  while(true){
    
    // Primal infeasability
    double pr_inf = primalInfeasibility(x_, lbx, ubx, gk_, lbg, ubg);
    
    // 1-norm of lagrange gradient
    double gLag_norm1 = norm_1(gLag_);
    
    // 1-norm of step
    double dx_norm1 = norm_1(dx_);
    
    // Print header occasionally
    if(iter % 10 == 0) printIteration(cout);
    
    // Printing information about the actual iterate
    printIteration(cout,iter,fk_,pr_inf,gLag_norm1,dx_norm1,reg_,ls_iter,ls_success);
    
    // Call callback function if present
    if (!callback_.isNull()) {
      callback_.input(NLP_COST).set(fk_);
      callback_.input(NLP_X_OPT).set(x_);
      callback_.input(NLP_LAMBDA_G).set(mu_);
      callback_.input(NLP_LAMBDA_X).set(mu_x_);
      callback_.input(NLP_G).set(gk_);
      callback_.evaluate();
      
      if (callback_.output(0).at(0)) {
        cout << endl;
        cout << "CasADi::SQPMethod: aborted by callback..." << endl;
        break;
      }
    }
    
    // Checking convergence criteria
    if (pr_inf < tol_pr_ && gLag_norm1 < tol_du_){
      cout << endl;
      cout << "CasADi::SQPMethod: Convergence achieved after " << iter << " iterations." << endl;
      break;
    }
    
    if (iter >= maxiter_){
      cout << endl;
      cout << "CasADi::SQPMethod: Maximum number of iterations reached." << endl;
      break;
    }
    
    // Start a new iteration
    iter++;
    
    // Formulate the QP
    transform(lbx.begin(),lbx.end(),x_.begin(),qp_LBX_.begin(),minus<double>());
    transform(ubx.begin(),ubx.end(),x_.begin(),qp_UBX_.begin(),minus<double>());
    transform(lbg.begin(),lbg.end(),gk_.begin(),qp_LBA_.begin(),minus<double>());
    transform(ubg.begin(),ubg.end(),gk_.begin(),qp_UBA_.begin(),minus<double>());

    // Solve the QP
    solve_QP(Bk_,gf_,qp_LBX_,qp_UBX_,Jk_,qp_LBA_,qp_UBA_,dx_,qp_DUAL_X_,qp_DUAL_A_);
    log("QP solved");

    // Detecting indefiniteness
    double gain = quad_form(dx_,Bk_);
    if (gain < 0){
      casadi_warning("Indefinite Hessian detected...");
    }
        
    // Calculate penalty parameter of merit function
    sigma_ = std::max(sigma_,1.01*norm_inf(qp_DUAL_X_));
    sigma_ = std::max(sigma_,1.01*norm_inf(qp_DUAL_A_));

    // Calculate L1-merit function in the actual iterate
    double l1_infeas = primalInfeasibility(x_, lbx, ubx, gk_, lbg, ubg);

    // Right-hand side of Armijo condition
    double F_sens = inner_prod(dx_, gf_);    
    double L1dir = F_sens - sigma_ * l1_infeas;
    double L1merit = fk_ + sigma_ * l1_infeas;

    // Storing the actual merit function value in a list
    merit_mem_.push_back(L1merit);
    if (merit_mem_.size() > merit_memsize_){
      merit_mem_.pop_front();
    }
    // Stepsize
    t = 1.0;
    double fk_cand;
    // Merit function value in candidate
    double L1merit_cand = 0;

    // Reset line-search counter, success marker
    ls_iter = 0;
    ls_success = true;

    // Line-search
    log("Starting line-search");
    if(maxiter_ls_>0){ // maxiter_ls_== 0 disables line-search
      
      // Line-search loop
      while (true){
        for(int i=0; i<n_; ++i) x_cand_[i] = x_[i] + t * dx_[i];
      
        // Evaluating objective and constraints
        eval_f(x_cand_,fk_cand);
        eval_g(x_cand_,gk_cand_);
        ls_iter++;

        // Calculating merit-function in candidate
        l1_infeas = primalInfeasibility(x_cand_, lbx, ubx, gk_cand_, lbg, ubg);
      
        L1merit_cand = fk_cand + sigma_ * l1_infeas;
        // Calculating maximal merit function value so far
        double meritmax = *max_element(merit_mem_.begin(), merit_mem_.end());
        if (L1merit_cand <= meritmax + t * c1_ * L1dir){
          // Accepting candidate
	  log("Line-search completed, candidate accepted");
          break;
        }
      
        // Line-search not successful, but we accept it.
        if(ls_iter == maxiter_ls_){
          ls_success = false;
	  log("Line-search completed, maximum number of iterations");
          break;
        }
      
        // Backtracking
        t = beta_ * t;
      }
    }

    // Candidate accepted, update dual variables
    for(int i=0; i<m_; ++i) mu_[i] = t * qp_DUAL_A_[i] + (1 - t) * mu_[i];
    for(int i=0; i<n_; ++i) mu_x_[i] = t * qp_DUAL_X_[i] + (1 - t) * mu_x_[i];
    
    if( hess_mode_ == HESS_BFGS){
      // Evaluate the gradient of the Lagrangian with the old x but new mu (for BFGS)
      copy(gf_.begin(),gf_.end(),gLag_old_.begin());
      if(m_>0) DMatrix::mul_no_alloc_tn(Jk_,mu_,gLag_old_);
      // gLag_old += mu_x_;
      transform(gLag_old_.begin(),gLag_old_.end(),mu_x_.begin(),gLag_old_.begin(),plus<double>());
    }
    
    // Candidate accepted, update the primal variable
    copy(x_.begin(),x_.end(),x_old_.begin());
    copy(x_cand_.begin(),x_cand_.end(),x_.begin());

    // Evaluate the constraint Jacobian
    log("Evaluating jac_g");
    eval_jac_g(x_,gk_,Jk_);
    
    // Evaluate the gradient of the objective function
    log("Evaluating grad_f");
    eval_grad_f(x_,fk_,gf_);
    
    // Evaluate the gradient of the Lagrangian with the new x and new mu
    copy(gf_.begin(),gf_.end(),gLag_.begin());
    if(m_>0) DMatrix::mul_no_alloc_tn(Jk_,mu_,gLag_);
    // gLag += mu_x_;
    transform(gLag_.begin(),gLag_.end(),mu_x_.begin(),gLag_.begin(),plus<double>());

    // Updating Lagrange Hessian
    if( hess_mode_ == HESS_BFGS){
      log("Updating Hessian (BFGS)");
      // BFGS with careful updates and restarts
      if (iter % lbfgs_memory_ == 0){
        // Reset Hessian approximation by dropping all off-diagonal entries
        const vector<int>& rowind = Bk_.rowind();      // Access sparsity (row offset)
        const vector<int>& col = Bk_.col();            // Access sparsity (column)
        vector<double>& data = Bk_.data();             // Access nonzero elements
        for(int i=0; i<rowind.size()-1; ++i){          // Loop over the rows of the Hessian
          for(int el=rowind[i]; el<rowind[i+1]; ++el){ // Loop over the nonzero elements of the row
            if(i!=col[el]) data[el] = 0;               // Remove if off-diagonal entries
          }
        }
      }
      
      // Pass to BFGS update function
      bfgs_.setInput(Bk_,BFGS_BK);
      bfgs_.setInput(x_,BFGS_X);
      bfgs_.setInput(x_old_,BFGS_X_OLD);
      bfgs_.setInput(gLag_,BFGS_GLAG);
      bfgs_.setInput(gLag_old_,BFGS_GLAG_OLD);
      
      // Update the Hessian approximation
      bfgs_.evaluate();
      
      // Get the updated Hessian
      bfgs_.getOutput(Bk_);
    } else {
      // Exact Hessian
      log("Evaluating hessian");
      eval_h(x_,mu_,1.0,Bk_);
    }
  }
  
  // Save results to outputs
  output(NLP_COST).set(fk_);
  output(NLP_X_OPT).set(x_);
  output(NLP_LAMBDA_G).set(mu_);
  output(NLP_LAMBDA_X).set(mu_x_);
  output(NLP_G).set(gk_);
  
  // Save statistics
  stats_["iter_count"] = iter;
}
Example #6
0
  void WorhpInternal::evaluate(){
    log("WorhpInternal::evaluate");
    
    if (gather_stats_) {
      Dictionary iterations;
      iterations["iter_sqp"] = std::vector<int>();
      iterations["inf_pr"] = std::vector<double>();
      iterations["inf_du"] = std::vector<double>();
      iterations["obj"] = std::vector<double>();
      iterations["alpha_pr"] = std::vector<double>();
      stats_["iterations"] = iterations;
    }
    
    // Prepare the solver
    reset();
    
    if (inputs_check_) checkInputs();
    checkInitialBounds();
  
    // Reset the counters
    t_eval_f_ = t_eval_grad_f_ = t_eval_g_ = t_eval_jac_g_ = t_eval_h_ = t_callback_fun_ = t_callback_prepare_ = t_mainloop_ = 0;
    
    n_eval_f_ = n_eval_grad_f_ = n_eval_g_ = n_eval_jac_g_ = n_eval_h_ = 0;
  
    // Get inputs
    log("WorhpInternal::evaluate: Reading user inputs");
    const DMatrix& x0 = input(NLP_SOLVER_X0);    
    const DMatrix& lbx = input(NLP_SOLVER_LBX);
    const DMatrix& ubx = input(NLP_SOLVER_UBX);
    const DMatrix& lam_x0 = input(NLP_SOLVER_LAM_X0);
    const DMatrix& lbg = input(NLP_SOLVER_LBG);
    const DMatrix& ubg = input(NLP_SOLVER_UBG);
    const DMatrix& lam_g0 = input(NLP_SOLVER_LAM_G0);

    double inf = numeric_limits<double>::infinity();  

    for (int i=0;i<nx_;++i) {
      casadi_assert_message(lbx.at(i)!=ubx.at(i),"WorhpSolver::evaluate: Worhp cannot handle the case when LBX == UBX. You have that case at non-zero " << i << " , which has value " << ubx.at(i) << ". Reformulate your problem by using a parameter for the corresponding variable.");
    }
  
    for (int i=0;i<lbg.size();++i) {
      casadi_assert_message(!(lbg.at(i)==-inf && ubg.at(i) == inf),"WorhpSolver::evaluate: Worhp cannot handle the case when both LBG and UBG are infinite. You have that case at non-zero " << i << ". Reformulate your problem eliminating the corresponding constraint.");
    }

    // Pass inputs to WORHP data structures
    x0.getArray(worhp_o_.X,worhp_o_.n);
    lbx.getArray(worhp_o_.XL,worhp_o_.n);
    ubx.getArray(worhp_o_.XU,worhp_o_.n);
    lam_x0.getArray(worhp_o_.Lambda,worhp_o_.n);
    if (worhp_o_.m>0){
      lam_g0.getArray(worhp_o_.Mu,worhp_o_.m);
      lbg.getArray(worhp_o_.GL,worhp_o_.m);
      ubg.getArray(worhp_o_.GU,worhp_o_.m);
    }

    // Replace infinite bounds with worhp_p_.Infty
    for(int i=0; i<nx_; ++i) if(worhp_o_.XL[i]==-inf) worhp_o_.XL[i] = -worhp_p_.Infty;
    for(int i=0; i<nx_; ++i) if(worhp_o_.XU[i]== inf) worhp_o_.XU[i] =  worhp_p_.Infty;
    for(int i=0; i<ng_; ++i) if(worhp_o_.GL[i]==-inf) worhp_o_.GL[i] = -worhp_p_.Infty;
    for(int i=0; i<ng_; ++i) if(worhp_o_.GU[i]== inf) worhp_o_.GU[i] =  worhp_p_.Infty;
  
    log("WorhpInternal::starting iteration");

    double time1 = clock();
  
    // Reverse Communication loop
    while(worhp_c_.status < TerminateSuccess &&  worhp_c_.status > TerminateError) {
      if (GetUserAction(&worhp_c_, callWorhp)) {
        Worhp(&worhp_o_, &worhp_w_, &worhp_p_, &worhp_c_);
      }


      if (GetUserAction(&worhp_c_, iterOutput)) {
            
        if (!worhp_w_.FirstIteration) {
          if (gather_stats_) {
            Dictionary & iterations = stats_["iterations"];
            static_cast<std::vector<int> &>(iterations["iter_sqp"]).push_back(worhp_w_.MinorIter);
            static_cast<std::vector<double> &>(iterations["inf_pr"]).push_back(worhp_w_.NormMax_CV);
            static_cast<std::vector<double> &>(iterations["inf_du"]).push_back(worhp_w_.ScaledKKT);
            static_cast<std::vector<double> &>(iterations["obj"]).push_back(worhp_o_.F);
            static_cast<std::vector<double> &>(iterations["alpha_pr"]).push_back(worhp_w_.ArmijoAlpha);
          }
        
          if (!callback_.isNull()) {
            double time1 = clock();
            // Copy outputs
            if (!output(NLP_SOLVER_X).isEmpty())
              output(NLP_SOLVER_X).setArray(worhp_o_.X,worhp_o_.n);
            if (!output(NLP_SOLVER_F).isEmpty())
              output(NLP_SOLVER_F).set(worhp_o_.F);
            if (!output(NLP_SOLVER_G).isEmpty())
              output(NLP_SOLVER_G).setArray(worhp_o_.G,worhp_o_.m);
            if (!output(NLP_SOLVER_LAM_X).isEmpty()) 
              output(NLP_SOLVER_LAM_X).setArray(worhp_o_.Lambda,worhp_o_.n);
            if (!output(NLP_SOLVER_LAM_G).isEmpty())
              output(NLP_SOLVER_LAM_G).setArray(worhp_o_.Mu,worhp_o_.m);
              
            Dictionary iteration;
            iteration["iter"] = worhp_w_.MajorIter;
            iteration["iter_sqp"] = worhp_w_.MinorIter;
            iteration["inf_pr"] = worhp_w_.NormMax_CV;
            iteration["inf_du"] = worhp_w_.ScaledKKT;
            iteration["obj"] = worhp_o_.F;
            iteration["alpha_pr"] = worhp_w_.ArmijoAlpha;
            stats_["iteration"] = iteration;

            double time2 = clock();
            t_callback_prepare_ += double(time2-time1)/CLOCKS_PER_SEC;
            time1 = clock();
            int ret = callback_(ref_,user_data_);
            time2 = clock();
            t_callback_fun_ += double(time2-time1)/CLOCKS_PER_SEC;
            
            if(ret) worhp_c_.status = TerminatedByUser;
            
          }
        }

    
        IterationOutput(&worhp_o_, &worhp_w_, &worhp_p_, &worhp_c_);
        DoneUserAction(&worhp_c_, iterOutput);
      }

      if (GetUserAction(&worhp_c_, evalF)) {
        eval_f(worhp_o_.X, worhp_w_.ScaleObj, worhp_o_.F);
        DoneUserAction(&worhp_c_, evalF);
      }

      if (GetUserAction(&worhp_c_, evalG)) {
        eval_g(worhp_o_.X, worhp_o_.G);
        DoneUserAction(&worhp_c_, evalG);
      }

      if (GetUserAction(&worhp_c_, evalDF)) {
        eval_grad_f(worhp_o_.X, worhp_w_.ScaleObj, worhp_w_.DF.val);
        DoneUserAction(&worhp_c_, evalDF);
      }

      if (GetUserAction(&worhp_c_, evalDG)) {
        eval_jac_g(worhp_o_.X,worhp_w_.DG.val);
        DoneUserAction(&worhp_c_, evalDG);
      }

      if (GetUserAction(&worhp_c_, evalHM)) {
        eval_h(worhp_o_.X, worhp_w_.ScaleObj, worhp_o_.Mu, worhp_w_.HM.val);
        DoneUserAction(&worhp_c_, evalHM);
      }
    
      if (GetUserAction(&worhp_c_, fidif)) {
        WorhpFidif(&worhp_o_, &worhp_w_, &worhp_p_, &worhp_c_);
      }
    }

    double time2 = clock();
    t_mainloop_ += double(time2-time1)/CLOCKS_PER_SEC;
  
    // Copy outputs
    output(NLP_SOLVER_X).setArray(worhp_o_.X,worhp_o_.n,DENSE);
    output(NLP_SOLVER_F).set(worhp_o_.F);
    output(NLP_SOLVER_G).setArray(worhp_o_.G,worhp_o_.m,DENSE);
    output(NLP_SOLVER_LAM_X).setArray(worhp_o_.Lambda,worhp_o_.n);
    output(NLP_SOLVER_LAM_G).setArray(worhp_o_.Mu,worhp_o_.m,DENSE);
  
    StatusMsg(&worhp_o_, &worhp_w_, &worhp_p_, &worhp_c_);
 
    if (hasOption("print_time") && bool(getOption("print_time"))) {
      // Write timings
      cout << "time spent in eval_f: " << t_eval_f_ << " s.";
      if (n_eval_f_>0)
        cout << " (" << n_eval_f_ << " calls, " << (t_eval_f_/n_eval_f_)*1000 << " ms. average)";
      cout << endl;
      cout << "time spent in eval_grad_f: " << t_eval_grad_f_ << " s.";
      if (n_eval_grad_f_>0)
        cout << " (" << n_eval_grad_f_ << " calls, " << (t_eval_grad_f_/n_eval_grad_f_)*1000 << " ms. average)";
      cout << endl;
      cout << "time spent in eval_g: " << t_eval_g_ << " s.";
      if (n_eval_g_>0)
        cout << " (" << n_eval_g_ << " calls, " << (t_eval_g_/n_eval_g_)*1000 << " ms. average)";
      cout << endl;
      cout << "time spent in eval_jac_g: " << t_eval_jac_g_ << " s.";
      if (n_eval_jac_g_>0)
        cout << " (" << n_eval_jac_g_ << " calls, " << (t_eval_jac_g_/n_eval_jac_g_)*1000 << " ms. average)";
      cout << endl;
      cout << "time spent in eval_h: " << t_eval_h_ << " s.";
      if (n_eval_h_>1)
        cout << " (" << n_eval_h_ << " calls, " << (t_eval_h_/n_eval_h_)*1000 << " ms. average)";
      cout << endl;
      cout << "time spent in main loop: " << t_mainloop_ << " s." << endl;
      cout << "time spent in callback function: " << t_callback_fun_ << " s." << endl;
      cout << "time spent in callback preparation: " << t_callback_prepare_ << " s." << endl;
    }
  
    stats_["t_eval_f"] = t_eval_f_;
    stats_["t_eval_grad_f"] = t_eval_grad_f_;
    stats_["t_eval_g"] = t_eval_g_;
    stats_["t_eval_jac_g"] = t_eval_jac_g_;
    stats_["t_eval_h"] = t_eval_h_;
    stats_["t_mainloop"] = t_mainloop_;
    stats_["t_callback_fun"] = t_callback_fun_;
    stats_["t_callback_prepare"] = t_callback_prepare_;
    stats_["n_eval_f"] = n_eval_f_;
    stats_["n_eval_grad_f"] = n_eval_grad_f_;
    stats_["n_eval_g"] = n_eval_g_;
    stats_["n_eval_jac_g"] = n_eval_jac_g_;
    stats_["n_eval_h"] = n_eval_h_;
    stats_["iter_count"] = worhp_w_.MajorIter;
    
    stats_["return_code"] = worhp_c_.status;
    stats_["return_status"] = flagmap[worhp_c_.status];
    
  }