void TRON::tron(double *w)
{
// Parameters for updating the iterates.
double eta0 = 1e-4, eta1 = 0.25, eta2 = 0.75;
// Parameters for updating the trust region size delta.
double sigma1 = 0.25, sigma2 = 0.5, sigma3 = 4;
Int n = fun_obj->get_nr_variable();
Int i, cg_iter;
double delta, snorm, one=1.0;
double alpha, f, fnew, prered, actred, gs;
Int search = 1, iter = 1, inc = 1;
double *s = new double[n];
double *r = new double[n];
double *g = new double[n];
// calculate gradient norm at w=0 for stopping condition.
double *w0 = new double[n];
for (i=0; i<n; i++)
w0[i] = 0;
fun_obj->fun(w0);
fun_obj->grad(w0, g);
double gnorm0 = dnrm2_(&n, g, &inc);
delete [] w0;
f = fun_obj->fun(w);
fun_obj->grad(w, g);
delta = dnrm2_(&n, g, &inc);
double gnorm = delta;
if (gnorm <= eps*gnorm0)
search = 0;
iter = 1;
double *w_new = new double[n];
while (iter <= max_iter && search)
{
cg_iter = trcg(delta, g, s, r);
memcpy(w_new, w, sizeof(double)*n);
daxpy_(&n, &one, s, &inc, w_new, &inc);
gs = ddot_(&n, g, &inc, s, &inc);
prered = -0.5*(gs-ddot_(&n, s, &inc, r, &inc));
fnew = fun_obj->fun(w_new);
// Compute the actual reduction.
actred = f - fnew;
// On the first iteration, adjust the initial step bound.
snorm = dnrm2_(&n, s, &inc);
if (iter == 1)
delta = min(delta, snorm);
// Compute prediction alpha*snorm of the step.
if (fnew - f - gs <= 0)
alpha = sigma3;
else
alpha = max(sigma1, -0.5*(gs/(fnew - f - gs)));
// Update the trust region bound according to the ratio of actual to predicted reduction.
if (actred < eta0*prered)
delta = min(max(alpha, sigma1)*snorm, sigma2*delta);
else if (actred < eta1*prered)
delta = max(sigma1*delta, min(alpha*snorm, sigma2*delta));
else if (actred < eta2*prered)
delta = max(sigma1*delta, min(alpha*snorm, sigma3*delta));
else
delta = max(delta, min(alpha*snorm, sigma3*delta));
info("iter %2d act %5.3e pre %5.3e delta %5.3e f %5.3e |g| %5.3e CG %3d\n", iter, actred, prered, delta, f, gnorm, cg_iter);
if (actred > eta0*prered)
{
iter++;
memcpy(w, w_new, sizeof(double)*n);
f = fnew;
fun_obj->grad(w, g);
gnorm = dnrm2_(&n, g, &inc);
if (gnorm <= eps*gnorm0)
break;
}
if (f < -1.0e+32)
{
info("WARNING: f < -1.0e+32\n");
break;
}
if (fabs(actred) <= 0 && prered <= 0)
{
info("WARNING: actred and prered <= 0\n");
break;
}
if (fabs(actred) <= 1.0e-12*fabs(f) &&
fabs(prered) <= 1.0e-12*fabs(f))
{
info("WARNING: actred and prered too small\n");
break;
}
}
delete[] g;
delete[] r;
delete[] w_new;
delete[] s;
}
void TRON::tron(double *w)
{
int i;
srand(0);
double eta = 1e-4;
int n = fun_obj->get_nr_variable();
int l = fun_obj->get_nr_instance();
double gnorm1, alpha, f, fnew, actred, gs;
int cg_iter, search = 1, iter = 1, inc = 1;
long int num_data = 0;
int *Hsample = new int[l];
double *s = new double[n];
double *r = new double[n];
double *w_new = new double[n];
double *g = new double[n];
for (i=0; i<l; i++)
Hsample[i] = rand() % num_sample;
for (i=0; i<n; i++)
{
s[i] = 0.0;
w[i] = 0.0;
}
f = fun_obj->fun(w, &num_data);
iter = 1;
fun_obj->grad(w, g, Hsample, iter, num_sample, &num_data);
gnorm1 = dnrm2_(&n, g, &inc);
double gnorm = gnorm1;
if (gnorm <= eps*gnorm1)
search = 0;
double sTs,shift_time = 0.0,cg_time = 0.0,line_search_time = 0.0;
const clock_t start = clock();
while (iter <= max_iter && search)
{
info("FUN %20.15e TIME %20.15e\n", f,(double)(clock()-start)/CLOCKS_PER_SEC);
const clock_t begin_time = clock();
cg_iter = trcg(g, s, r, num_sample,&num_data);
cg_time = float(clock() - begin_time)/CLOCKS_PER_SEC;
gs = ddot_(&n, g, &inc, s, &inc);
// ***Method 1***
if(num_sample == 1)
{
alpha = 1;
}else{
sTs = ddot_(&n, s, &inc, s, &inc);
fun_obj->get_alpha(&alpha, gs, sTs, s, &num_data);
for(i=0;i<n;i++)
s[i] *= alpha;
gs = alpha*gs;
alpha = 1;
}
const clock_t line_begin_time = clock();
alpha = 1;
while(1)
{
memcpy(w_new, w, sizeof(double)*n);
daxpy_(&n, &alpha, s, &inc, w_new, &inc);
fnew = fun_obj->fun(w_new,&num_data);
actred = f - fnew;
if (actred+eta*alpha*gs >= 0)
break;
alpha /= 2;
}
line_search_time = float( clock() - line_begin_time)/CLOCKS_PER_SEC;
memcpy(w, w_new, sizeof(double)*n);
f = fnew;
fun_obj->grad(w, g, Hsample, iter+1, num_sample,&num_data);
gnorm = dnrm2_(&n, g, &inc);
shift_time += float(clock() - begin_time)/CLOCKS_PER_SEC;
info("iter %2d act %5.3e fun %5.3e |g| %5.3e CG %3d cg_time: %g line_search_time: %g time %.6f num_data %ld f %.16f alpha %g\n", iter, actred, f, gnorm, cg_iter, cg_time, line_search_time, shift_time, num_data, f, alpha);
iter++;
if (gnorm <= eps*gnorm1)
break;
if(fabs(actred) <= 1.0e-12*fabs(f))
{
printf("actual reduction is too small");
break;
}
if (f < -1.0e+32)
{
info("WARNING: f < -1.0e+32\n");
break;
}
}
delete[] g;
delete[] r;
delete[] w_new;
delete[] s;
delete[] Hsample;
}
