{"id":"W1772464306","doi":"10.48550/arxiv.1502.04390","title":"Equilibrated adaptive learning rates for non-convex optimization","year":2015,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Preconditioner; Hessian matrix; Saddle point; Computer science; Mathematical optimization; Rate of convergence; Curvature; Eigenvalues and eigenvectors; Convergence (economics); Stochastic gradient descent; Scheme (mathematics); Adaptive learning; Regular polygon; Convex optimization; Artificial neural network; Artificial intelligence; Applied mathematics; Mathematics; Iterative method; Mathematical analysis","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002128585,0.0001427433,0.0001491755,0.0001981706,0.0001252055,0.00007696296,0.0005728839,0.0000832528,0.00001014058],"category_scores_gemma":[0.0001428082,0.000163866,0.00005525902,0.0008759287,0.00005857089,0.0009301857,0.0001835413,0.00009619129,0.00001966904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001062144,"about_ca_system_score_gemma":0.0001180269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001195665,"about_ca_topic_score_gemma":8.777441e-7,"domain_scores_codex":[0.9990431,0.00005872872,0.0001256096,0.0004647235,0.0000641186,0.0002437404],"domain_scores_gemma":[0.9989008,0.0001195707,0.0001329519,0.0002912162,0.0003993879,0.0001560635],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003336601,0.00002483443,0.0003941544,0.000002564936,0.00001413687,0.000007282842,0.0001990233,0.8871418,0.00002578929,0.1117157,0.0003393031,0.0001021131],"study_design_scores_gemma":[0.0006934644,0.0002868574,0.00001716607,0.00001417664,0.00001294706,0.000001999273,0.0001487431,0.9905705,0.001035232,0.006966951,0.00005998023,0.0001919615],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003586958,0.000007729024,0.9937822,0.00005023585,0.0001545047,0.0003462391,0.000001644245,0.0005067092,0.001563768],"genre_scores_gemma":[0.8511732,0.000005190185,0.1479545,0.00005426109,0.00002081063,0.000002961497,0.00001241062,0.00001347224,0.0007632221],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8475862,"threshold_uncertainty_score":0.6682262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09230213855191799,"score_gpt":0.211123693247461,"score_spread":0.118821554695543,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}