int run_em(EM_ENG_PTR em_ptr)
{
int r, iterate, old_valid, converged, saved = 0;
double likelihood, log_prior;
double lambda, old_lambda = 0.0;
config_em(em_ptr);
for (r = 0; r < num_restart; r++) {
SHOW_PROGRESS_HEAD("#em-iters", r);
initialize_params();
itemp = daem ? itemp_init : 1.0;
iterate = 0;
/* [21 Aug 2007, by yuizumi]
* while-loop for inversed temperature (DAEM). Note that this
* loop is evaluated only once for EM without annealing, since
* itemp initially set to 1.0 by the code above.
*/
while (1) {
if (daem) {
SHOW_PROGRESS_TEMP(itemp);
}
old_valid = 0;
while (1) {
if (CTRLC_PRESSED) {
SHOW_PROGRESS_INTR();
RET_ERR(err_ctrl_c_pressed);
}
RET_ON_ERR(em_ptr->compute_inside());
RET_ON_ERR(em_ptr->examine_inside());
likelihood = em_ptr->compute_likelihood();
log_prior = em_ptr->smooth ? em_ptr->compute_log_prior() : 0.0;
lambda = likelihood + log_prior;
if (verb_em) {
if (em_ptr->smooth) {
prism_printf("Iteration #%d:\tlog_likelihood=%.9f\tlog_prior=%.9f\tlog_post=%.9f\n", iterate, likelihood, log_prior, lambda);
}
else {
prism_printf("Iteration #%d:\tlog_likelihood=%.9f\n", iterate, likelihood);
}
}
if (debug_level) {
prism_printf("After I-step[%d]:\n", iterate);
prism_printf("likelihood = %.9f\n", likelihood);
print_egraph(debug_level, PRINT_EM);
}
if (!isfinite(lambda)) {
emit_internal_error("invalid log likelihood or log post: %s (at iteration #%d)",
isnan(lambda) ? "NaN" : "infinity", iterate);
RET_ERR(ierr_invalid_likelihood);
}
if (old_valid && old_lambda - lambda > prism_epsilon) {
emit_error("log likelihood or log post decreased [old: %.9f, new: %.9f] (at iteration #%d)",
old_lambda, lambda, iterate);
RET_ERR(err_invalid_likelihood);
}
if (itemp == 1.0 && likelihood > 0.0) {
emit_error("log likelihood greater than zero [value: %.9f] (at iteration #%d)",
likelihood, iterate);
RET_ERR(err_invalid_likelihood);
}
converged = (old_valid && lambda - old_lambda <= prism_epsilon);
if (converged || REACHED_MAX_ITERATE(iterate)) {
break;
}
old_lambda = lambda;
old_valid = 1;
RET_ON_ERR(em_ptr->compute_expectation());
if (debug_level) {
prism_printf("After O-step[%d]:\n", iterate);
print_egraph(debug_level, PRINT_EM);
}
SHOW_PROGRESS(iterate);
RET_ON_ERR(em_ptr->update_params());
iterate++;
}
/* [21 Aug 2007, by yuizumi]
* Note that 1.0 can be represented exactly in IEEE 754.
*/
if (itemp == 1.0) {
break;
}
itemp *= itemp_rate;
if (itemp >= 1.0) {
itemp = 1.0;
}
}
SHOW_PROGRESS_TAIL(converged, iterate, lambda);
if (r == 0 || lambda > em_ptr->lambda) {
em_ptr->lambda = lambda;
em_ptr->likelihood = likelihood;
em_ptr->iterate = iterate;
saved = (r < num_restart - 1);
if (saved) {
save_params();
}
}
}
if (saved) {
restore_params();
}
em_ptr->bic = compute_bic(em_ptr->likelihood);
em_ptr->cs = em_ptr->smooth ? compute_cs(em_ptr->likelihood) : 0.0;
return BP_TRUE;
}
/* main loop */
static int run_grd(CRF_ENG_PTR crf_ptr) {
int r,iterate,old_valid,converged,conv_time,saved = 0;
double likelihood,old_likelihood = 0.0;
double crf_max_iterate = 0.0;
double tmp_epsilon,alpha0,gf_sd,old_gf_sd = 0.0;
config_crf(crf_ptr);
initialize_weights();
if (crf_learn_mode == 1) {
initialize_LBFGS();
printf("L-BFGS mode\n");
}
if (crf_learning_rate==1) {
printf("learning rate:annealing\n");
} else if (crf_learning_rate==2) {
printf("learning rate:backtrack\n");
} else if (crf_learning_rate==3) {
printf("learning rate:golden section\n");
}
if (max_iterate == -1) {
crf_max_iterate = DEFAULT_MAX_ITERATE;
} else if (max_iterate >= +1) {
crf_max_iterate = max_iterate;
}
for (r = 0; r < num_restart; r++) {
SHOW_PROGRESS_HEAD("#crf-iters", r);
initialize_crf_count();
initialize_lambdas();
initialize_visited_flags();
old_valid = 0;
iterate = 0;
tmp_epsilon = crf_epsilon;
LBFGS_index = 0;
conv_time = 0;
while (1) {
if (CTRLC_PRESSED) {
SHOW_PROGRESS_INTR();
RET_ERR(err_ctrl_c_pressed);
}
RET_ON_ERR(crf_ptr->compute_feature());
crf_ptr->compute_crf_probs();
likelihood = crf_ptr->compute_likelihood();
if (verb_em) {
prism_printf("Iteration #%d:\tlog_likelihood=%.9f\n", iterate, likelihood);
}
if (debug_level) {
prism_printf("After I-step[%d]:\n", iterate);
prism_printf("likelihood = %.9f\n", likelihood);
print_egraph(debug_level, PRINT_EM);
}
if (!isfinite(likelihood)) {
emit_internal_error("invalid log likelihood: %s (at iteration #%d)",
isnan(likelihood) ? "NaN" : "infinity", iterate);
RET_ERR(ierr_invalid_likelihood);
}
/* if (old_valid && old_likelihood - likelihood > prism_epsilon) {
emit_error("log likelihood decreased [old: %.9f, new: %.9f] (at iteration #%d)",
old_likelihood, likelihood, iterate);
RET_ERR(err_invalid_likelihood);
}*/
if (likelihood > 0.0) {
emit_error("log likelihood greater than zero [value: %.9f] (at iteration #%d)",
likelihood, iterate);
RET_ERR(err_invalid_likelihood);
}
if (crf_learn_mode == 1 && iterate > 0) restore_old_gradient();
RET_ON_ERR(crf_ptr->compute_gradient());
if (crf_learn_mode == 1 && iterate > 0) {
compute_LBFGS_y_rho();
compute_hessian(iterate);
} else if (crf_learn_mode == 1 && iterate == 0) {
initialize_LBFGS_q();
}
converged = (old_valid && fabs(likelihood - old_likelihood) <= prism_epsilon);
if (converged || REACHED_MAX_ITERATE(iterate)) {
break;
}
old_likelihood = likelihood;
old_valid = 1;
if (debug_level) {
prism_printf("After O-step[%d]:\n", iterate);
print_egraph(debug_level, PRINT_EM);
}
SHOW_PROGRESS(iterate);
if (crf_learning_rate == 1) { // annealing
tmp_epsilon = (annealing_weight / (annealing_weight + iterate)) * crf_epsilon;
} else if (crf_learning_rate == 2) { // line-search(backtrack)
if (crf_learn_mode == 1) {
gf_sd = compute_gf_sd_LBFGS();
} else {
gf_sd = compute_gf_sd();
}
if (iterate==0) {
alpha0 = 1;
} else {
alpha0 = tmp_epsilon * old_gf_sd / gf_sd;
}
if (crf_learn_mode == 1) {
tmp_epsilon = line_search_LBFGS(crf_ptr,alpha0,crf_ls_rho,crf_ls_c1,likelihood,gf_sd);
} else {
tmp_epsilon = line_search(crf_ptr,alpha0,crf_ls_rho,crf_ls_c1,likelihood,gf_sd);
}
if (tmp_epsilon < EPS) {
emit_error("invalid alpha in line search(=0.0) (at iteration #%d)",iterate);
RET_ERR(err_line_search);
}
old_gf_sd = gf_sd;
} else if (crf_learning_rate == 3) { // line-search(golden section)
if (crf_learn_mode == 1) {
tmp_epsilon = golden_section_LBFGS(crf_ptr,0,crf_golden_b);
} else {
tmp_epsilon = golden_section(crf_ptr,0,crf_golden_b);
}
}
crf_ptr->update_lambdas(tmp_epsilon);
iterate++;
}
SHOW_PROGRESS_TAIL(converged, iterate, likelihood);
if (r == 0 || likelihood > crf_ptr->likelihood) {
crf_ptr->likelihood = likelihood;
crf_ptr->iterate = iterate;
saved = (r < num_restart - 1);
if (saved) {
save_params();
}
}
}
if (crf_learn_mode == 1) clean_LBFGS();
INIT_VISITED_FLAGS;
return BP_TRUE;
}
int mpm_run_em(EM_ENG_PTR emptr) {
int r, iterate, old_valid, converged, saved=0;
double likelihood, log_prior;
double lambda, old_lambda=0.0;
config_em(emptr);
for (r = 0; r < num_restart; r++) {
SHOW_PROGRESS_HEAD("#em-iters", r);
initialize_params();
mpm_bcast_inside();
clear_sw_msg_send();
itemp = daem ? itemp_init : 1.0;
iterate = 0;
while (1) {
if (daem) {
SHOW_PROGRESS_TEMP(itemp);
}
old_valid = 0;
while (1) {
if (CTRLC_PRESSED) {
SHOW_PROGRESS_INTR();
RET_ERR(err_ctrl_c_pressed);
}
if (failure_observed) {
inside_failure = mp_sum_value(0.0);
}
log_prior = emptr->smooth ? emptr->compute_log_prior() : 0.0;
lambda = mp_sum_value(log_prior);
likelihood = lambda - log_prior;
mp_debug("local lambda = %.9f, lambda = %.9f", log_prior, lambda);
if (verb_em) {
if (emptr->smooth) {
prism_printf("Iteration #%d:\tlog_likelihood=%.9f\tlog_prior=%.9f\tlog_post=%.9f\n", iterate, likelihood, log_prior, lambda);
} else {
prism_printf("Iteration #%d:\tlog_likelihood=%.9f\n", iterate, likelihood);
}
}
if (!isfinite(lambda)) {
emit_internal_error("invalid log likelihood or log post: %s (at iterateion #%d)",
isnan(lambda) ? "NaN" : "infinity", iterate);
RET_ERR(ierr_invalid_likelihood);
}
if (old_valid && old_lambda - lambda > prism_epsilon) {
emit_error("log likelihood or log post decreased [old: %.9f, new: %.9f] (at iteration #%d)",
old_lambda, lambda, iterate);
RET_ERR(err_invalid_likelihood);
}
if (itemp == 1.0 && likelihood > 0.0) {
emit_error("log likelihood greater than zero [value: %.9f] (at iteration #%d)",
likelihood, iterate);
RET_ERR(err_invalid_likelihood);
}
converged = (old_valid && lambda - old_lambda <= prism_epsilon);
if (converged || REACHED_MAX_ITERATE(iterate)) {
break;
}
old_lambda = lambda;
old_valid = 1;
mpm_share_expectation();
SHOW_PROGRESS(iterate);
RET_ON_ERR(emptr->update_params());
iterate++;
}
if (itemp == 1.0) {
break;
}
itemp *= itemp_rate;
if (itemp >= 1.0) {
itemp = 1.0;
}
}
SHOW_PROGRESS_TAIL(converged, iterate, lambda);
if (r == 0 || lambda > emptr->lambda) {
emptr->lambda = lambda;
emptr->likelihood = likelihood;
emptr->iterate = iterate;
saved = (r < num_restart - 1);
if (saved) {
save_params();
}
}
}
if (saved) {
restore_params();
}
emptr->bic = compute_bic(emptr->likelihood);
emptr->cs = emptr->smooth ? compute_cs(emptr->likelihood) : 0.0;
return BP_TRUE;
}
