{"id":"W2136058147","doi":"10.48550/arxiv.1206.6464","title":"Estimating the Hessian by Back-propagating Curvature","year":2012,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Model Reduction and Neural Networks","field":"Physics and Astronomy","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Hessian matrix; Quasi-Newton method; Diagonal; Curvature; Applied mathematics; Mathematical optimization; Hessian equation; Matching (statistics); Mathematics; Function (biology); Rank (graph theory); Computer science; Algorithm; Combinatorics; Mathematical analysis; Newton's method; Geometry; Statistics; Physics; Partial differential equation","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":[0.00009341865,0.0001101255,0.00008410139,0.00001549469,0.0002746216,0.00002767388,0.0001695142,0.0000333924,0.0007534434],"category_scores_gemma":[0.000002213623,0.00008561924,0.00006894168,0.0002147429,0.00005370598,0.0002829038,0.00005583333,0.0002358141,0.0001571788],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001554795,"about_ca_system_score_gemma":0.000009496339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004426114,"about_ca_topic_score_gemma":6.095031e-7,"domain_scores_codex":[0.9993907,0.0000549701,0.00007544789,0.0001724,0.00003366627,0.0002728254],"domain_scores_gemma":[0.9995713,0.00003055461,0.00008102111,0.0001943566,0.0000201192,0.0001027141],"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":[0.00005481573,0.0004025459,0.2717768,0.00003703325,0.0002648745,0.000006238379,0.001085276,0.2001928,0.0016269,0.4280363,0.07295136,0.02356502],"study_design_scores_gemma":[0.000653535,0.00002619312,0.00128718,0.00005147161,0.00009433817,0.000003422503,0.000975919,0.9721863,0.001470389,0.005412519,0.01731465,0.0005240283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8456513,0.00005334275,0.1251572,0.0001791849,0.0004754516,0.0001367947,0.000008031638,0.00004856189,0.02829017],"genre_scores_gemma":[0.9951069,0.000001098715,0.000315259,0.00008451181,0.0005032812,3.817368e-7,0.00001200619,0.00001081031,0.003965709],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7719935,"threshold_uncertainty_score":0.8249677,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04490437076525512,"score_gpt":0.1848018931534511,"score_spread":0.139897522388196,"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."}}