{"id":"W2943463079","doi":"10.48550/arxiv.1904.13262","title":"Implicit Regularization of Discrete Gradient Dynamics in Linear Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":27,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Initialization; Regularization (linguistics); Parameterized complexity; Artificial neural network; Convergence (economics); Computer science; Applied mathematics; Rank (graph theory); Gradient descent; Algorithm; Mathematical optimization; Mathematics; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001088081,0.000807219,0.0005102642,0.0003360967,0.0002248893,0.000834531,0.0006522136,0.001079564,0.001616681],"category_scores_gemma":[0.006568654,0.0004367364,0.0003020718,0.0002991451,0.001661217,0.001701263,0.001357706,0.001824685,0.0003200416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000771737,"about_ca_system_score_gemma":0.0004756337,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001694628,"about_ca_topic_score_gemma":0.001922665,"domain_scores_codex":[0.9995342,0.0002239626,0.00001705516,0.00007116801,0.0001167785,0.00003681294],"domain_scores_gemma":[0.9987318,0.000843796,0.0001410267,0.0001251633,0.0001022907,0.00005594144],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008103913,0.00004230829,0.000544872,0.0001402731,0.00002722773,0.0001026295,0.0002038146,0.7670167,0.008916006,0.1968141,0.001517897,0.02459325],"study_design_scores_gemma":[0.000002914243,0.000009105946,0.00004272381,0.000005094103,8.550007e-7,0.000008979171,0.000004402201,0.9825799,0.0004015378,0.01673215,0.0002094228,0.000002937318],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03269544,0.0004161403,0.962743,0.0006668051,0.00004202344,0.0000226933,0.0000473034,0.0002694433,0.003097249],"genre_scores_gemma":[0.8492492,0.0007685328,0.1410379,0.0002356266,0.0001094663,0.0001420839,0.0001550879,0.0002469883,0.008055147],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.001694628,"threshold_uncertainty_score":0.005754411,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02612952777006198,"score_gpt":0.1747604210850382,"score_spread":0.1486308933149762,"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."}}