{"id":"W2965944281","doi":"","title":"Tight analyses for non-smooth stochastic gradient descent","year":2019,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics; Lipschitz continuity; Stochastic gradient descent; Differentiable function; Combinatorics; Convex function; Gradient descent; Upper and lower bounds; Regular polygon; Discrete mathematics; Applied mathematics; Mathematical analysis; Computer science","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":[0.0005947166,0.0002354505,0.0002738703,0.0002781158,0.0001679565,0.0001664508,0.0008620302,0.00008204028,0.0001298394],"category_scores_gemma":[0.0003178318,0.0002078406,0.0001164269,0.0002920722,0.00007214987,0.000195667,0.0001487141,0.0002522494,0.0001956096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007927304,"about_ca_system_score_gemma":0.0001055896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002074141,"about_ca_topic_score_gemma":4.294957e-7,"domain_scores_codex":[0.9983742,0.0001141738,0.0002524087,0.0005896972,0.0002756598,0.0003939056],"domain_scores_gemma":[0.9982857,0.0005610347,0.000192769,0.0006202292,0.0002181232,0.0001222132],"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":[0.00005276585,0.00007526689,0.00007659453,0.00002195348,0.00002811702,0.000001341607,0.0007526672,0.02500296,0.001196654,0.9558377,0.0002062691,0.0167477],"study_design_scores_gemma":[0.000717464,0.001096972,0.0005848994,0.0002507227,0.00002656131,0.000004572322,0.0001863529,0.9044617,0.002341426,0.08919884,0.0006373452,0.0004931325],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.006060097,0.00002328467,0.9870684,0.0001723001,0.0004085263,0.0006415672,0.000001672178,0.0004546574,0.005169563],"genre_scores_gemma":[0.9603824,0.000005460807,0.03630149,0.0001837702,0.00003467724,0.0001079622,0.000009469995,0.00002459272,0.002950154],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9543223,"threshold_uncertainty_score":0.8475491,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04690993015189428,"score_gpt":0.3102476221312967,"score_spread":0.2633376919794024,"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."}}