/* [Note] node copying is not required here even in computation without
* inter-goal sharing, but we need to declare it explicitly.
*/
int pc_compute_viterbi_5(void)
{
TERM p_goal_path,p_subpath_goal,p_subpath_sw;
int goal_id;
double viterbi_prob;
goal_id = bpx_get_integer(bpx_get_call_arg(1,5));
initialize_egraph_index();
alloc_sorted_egraph(1);
/* INIT_MIN_MAX_NODE_NOS; */
RET_ON_ERR(sort_one_egraph(goal_id,0,1));
if (verb_graph) print_egraph(0,PRINT_NEUTRAL);
compute_max();
if (debug_level) print_egraph(1,PRINT_VITERBI);
get_most_likely_path(goal_id,&p_goal_path,&p_subpath_goal,
&p_subpath_sw,&viterbi_prob);
return
bpx_unify(bpx_get_call_arg(2,5), p_goal_path) &&
bpx_unify(bpx_get_call_arg(3,5), p_subpath_goal) &&
bpx_unify(bpx_get_call_arg(4,5), p_subpath_sw) &&
bpx_unify(bpx_get_call_arg(5,5), bpx_build_float(viterbi_prob));
}
int pc_compute_inside_2(void)
{
int gid;
double prob;
EG_NODE_PTR eg_ptr;
gid = bpx_get_integer(bpx_get_call_arg(1,2));
initialize_egraph_index();
alloc_sorted_egraph(1);
RET_ON_ERR(sort_one_egraph(gid, 0, 1));
if (verb_graph) {
print_egraph(0, PRINT_NEUTRAL);
}
eg_ptr = expl_graph[gid];
if (log_scale) {
RET_ON_ERR(compute_inside_scaling_log_exp());
prob = eg_ptr->inside;
}
else {
RET_ON_ERR(compute_inside_scaling_none());
prob = eg_ptr->inside;
}
return bpx_unify(bpx_get_call_arg(2,2), bpx_build_float(prob));
}
int pc_crf_prepare_4(void) {
TERM p_fact_list;
int size;
p_fact_list = bpx_get_call_arg(1,4);
size = bpx_get_integer(bpx_get_call_arg(2,4));
num_goals = bpx_get_integer(bpx_get_call_arg(3,4));
failure_root_index = bpx_get_integer(bpx_get_call_arg(4,4));
failure_observed = (failure_root_index != -1);
if (failure_root_index != -1) {
failure_subgoal_id = prism_goal_id_get(failure_atom);
if (failure_subgoal_id == -1) {
emit_internal_error("no subgoal ID allocated to `failure'");
RET_INTERNAL_ERR;
}
}
initialize_egraph_index();
alloc_sorted_egraph(size);
RET_ON_ERR(sort_crf_egraphs(p_fact_list));
#ifndef MPI
if (verb_graph) {
print_egraph(0, PRINT_NEUTRAL);
}
#endif /* !(MPI) */
alloc_occ_switches();
alloc_num_sw_vals();
return BP_TRUE;
}
/*
* Note: parameters are always refreshed in advance by $pc_export_sw_info/1,
* so it causes no problem to overwrite them temporarily
*/
int pc_compute_n_viterbi_rerank_4(void)
{
TERM p_n_viterbi_list;
int n,l,goal_id;
n = bpx_get_integer(bpx_get_call_arg(1,4));
l = bpx_get_integer(bpx_get_call_arg(2,4));
goal_id = bpx_get_integer(bpx_get_call_arg(3,4));
initialize_egraph_index();
alloc_sorted_egraph(1);
/* INIT_MIN_MAX_NODE_NOS; */
RET_ON_ERR(sort_one_egraph(goal_id,0,1));
if (verb_graph) print_egraph(0,PRINT_NEUTRAL);
alloc_occ_switches();
transfer_hyperparams_prolog();
get_param_means();
compute_n_max(l);
get_n_most_likely_path_rerank(n,l,goal_id,&p_n_viterbi_list);
release_occ_switches();
return bpx_unify(bpx_get_call_arg(4,4),p_n_viterbi_list);
}
int pc_compute_n_viterbi_3(void)
{
TERM p_n_viterbi_list;
int n,goal_id;
n = bpx_get_integer(bpx_get_call_arg(1,3));
goal_id = bpx_get_integer(bpx_get_call_arg(2,3));
initialize_egraph_index();
alloc_sorted_egraph(1);
/* INIT_MIN_MAX_NODE_NOS; */
RET_ON_ERR(sort_one_egraph(goal_id,0,1));
if (verb_graph) print_egraph(0,PRINT_NEUTRAL);
compute_n_max(n);
if (debug_level) print_egraph(1,PRINT_VITERBI);
get_n_most_likely_path(n,goal_id,&p_n_viterbi_list);
return bpx_unify(bpx_get_call_arg(3,3),p_n_viterbi_list);
}
/* 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 pc_compute_hindsight_4(void)
{
TERM p_subgoal,p_hindsight_pairs,t,t1,p_pair;
int goal_id,is_cond,j;
goal_id = bpx_get_integer(bpx_get_call_arg(1,4));
p_subgoal = bpx_get_call_arg(2,4);
is_cond = bpx_get_integer(bpx_get_call_arg(3,4));
initialize_egraph_index();
alloc_sorted_egraph(1);
RET_ON_ERR(sort_one_egraph(goal_id,0,1));
if (verb_graph) print_egraph(0,PRINT_NEUTRAL);
alloc_hindsight_goals();
if (log_scale) {
RET_ON_ERR(compute_inside_scaling_log_exp());
RET_ON_ERR(compute_outside_scaling_log_exp());
RET_ON_ERR(get_hindsight_goals_scaling_log_exp(p_subgoal,is_cond));
}
else {
RET_ON_ERR(compute_inside_scaling_none());
RET_ON_ERR(compute_outside_scaling_none());
RET_ON_ERR(get_hindsight_goals_scaling_none(p_subgoal,is_cond));
}
if (hindsight_goal_size > 0) {
/* Build the list of pairs of a subgoal and its hindsight probability */
p_hindsight_pairs = bpx_build_list();
t = p_hindsight_pairs;
for (j = 0; j < hindsight_goal_size; j++) {
p_pair = bpx_build_list();
t1 = p_pair;
bpx_unify(bpx_get_car(t1),
bpx_build_integer(hindsight_goals[j]));
bpx_unify(bpx_get_cdr(t1),bpx_build_list());
t1 = bpx_get_cdr(t1);
bpx_unify(bpx_get_car(t1),bpx_build_float(hindsight_probs[j]));
bpx_unify(bpx_get_cdr(t1),bpx_build_nil());
bpx_unify(bpx_get_car(t),p_pair);
if (j == hindsight_goal_size - 1) {
bpx_unify(bpx_get_cdr(t),bpx_build_nil());
}
else {
bpx_unify(bpx_get_cdr(t),bpx_build_list());
t = bpx_get_cdr(t);
}
}
}
else {
p_hindsight_pairs = bpx_build_nil();
}
FREE(hindsight_goals);
FREE(hindsight_probs);
return bpx_unify(bpx_get_call_arg(4,4),p_hindsight_pairs);
}
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;
}