{"id":"W2971899460","doi":"10.48550/arxiv.1909.00843","title":"Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stochastic gradient descent; Simple (philosophy); Mathematics; Rate of convergence; Convex function; Applied mathematics; Generalization; Convergence (economics); Gradient descent; Regular polygon; Mathematical optimization; Computer science; Artificial neural network; 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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003680247,0.0004738611,0.0005480553,0.0003070166,0.0002192549,0.0002343899,0.001510998,0.0003250906,0.0000148037],"category_scores_gemma":[0.0001168907,0.0005504857,0.0002082596,0.0003497098,0.0002429561,0.0003542939,0.00217952,0.0004125388,0.00001016618],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004831995,"about_ca_system_score_gemma":0.000255651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001040547,"about_ca_topic_score_gemma":0.00001235926,"domain_scores_codex":[0.997091,0.00009077195,0.0003357928,0.001755649,0.0001466568,0.0005801098],"domain_scores_gemma":[0.9972284,0.0002764201,0.000352054,0.001536402,0.0003397982,0.0002668769],"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":[0.00004302073,0.0001020734,0.0005068305,0.0001218022,0.00005955279,0.00000708261,0.0001237484,0.6646289,0.000005945094,0.334051,0.0001636599,0.0001864942],"study_design_scores_gemma":[0.0007390586,0.0002574579,0.0008883569,0.00006175516,0.000086778,0.00000306767,0.00002741198,0.8700152,0.00006740158,0.1272864,0.00005163053,0.0005154526],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1815398,0.00003719891,0.8157301,0.00005925564,0.0005954064,0.001508717,0.00006790023,0.0004085129,0.00005306903],"genre_scores_gemma":[0.9433139,0.00001631435,0.05628862,0.00004170993,0.00004713309,0.00001676659,0.00005887553,0.00003038954,0.0001862679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7617741,"threshold_uncertainty_score":0.9996946,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05756934174908965,"score_gpt":0.1974791108620137,"score_spread":0.139909769112924,"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."}}