{"id":"W2788204593","doi":"10.1145/3152494.3152498","title":"Are saddles good enough for neural networks","year":2018,"lang":"en","type":"article","venue":"","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Maxima and minima; MNIST database; Degeneracy (biology); Artificial neural network; Saddle point; Gradient descent; Computer science; Saddle; Convergence (economics); Perspective (graphical); Work (physics); Deep neural networks; Artificial intelligence; Mathematical optimization; Machine learning; Mathematics; Engineering; Geometry; Economics; Mathematical analysis","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009671448,0.00009053366,0.0000929153,0.00005407256,0.0001207694,0.0001013219,0.0005462008,0.00004745903,0.00002494626],"category_scores_gemma":[0.00006147298,0.00007755117,0.00004236695,0.0002203086,0.0000529586,0.0002241953,0.0001312314,0.00003705867,0.000008442456],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001469153,"about_ca_system_score_gemma":0.000007873714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003945502,"about_ca_topic_score_gemma":0.000006594973,"domain_scores_codex":[0.9992763,0.00001232715,0.0001320828,0.0002562977,0.00009814337,0.0002248393],"domain_scores_gemma":[0.9992712,0.00007005822,0.00009364168,0.0003513128,0.0001591785,0.00005462369],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000008707285,0.00006369791,0.0004938534,0.000006800642,0.00001505372,0.000001698075,0.0002345439,0.00420229,0.00002237346,0.9292123,0.0414382,0.02430054],"study_design_scores_gemma":[0.0001295582,0.0001503828,0.000365244,0.000006133728,0.000002477302,0.000005236533,0.00001033821,0.9900397,0.0007835171,0.005845263,0.002547937,0.0001142193],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002155992,0.00002315578,0.994754,0.001037122,0.0004442168,0.0002563563,0.000001407624,0.0006700414,0.002598111],"genre_scores_gemma":[0.4829732,0.000001003178,0.5148148,0.001173188,0.0002339634,0.00005305164,0.000001741096,0.000009166238,0.000739853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9858374,"threshold_uncertainty_score":0.3162445,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02769192627769521,"score_gpt":0.2642360515460286,"score_spread":0.2365441252683334,"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."}}