{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01417885,0.005382857,0.003560629,0.003378478,0.001922045,0.004896234,0.005649495,0.005257218,0.006634397],"category_scores_gemma":[0.08220223,0.001619985,0.002247155,0.003005784,0.006434483,0.01045598,0.007446191,0.008197201,0.002176876],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004021506,"about_ca_system_score_gemma":0.003604394,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001875885,"about_ca_topic_score_gemma":0.002407869,"domain_scores_codex":[0.9897413,0.004399617,0.0005112367,0.001522832,0.003078005,0.0007469109],"domain_scores_gemma":[0.949759,0.03679534,0.003058539,0.004442494,0.00450909,0.001435478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0003060361,0.0002816126,0.001084103,0.0005600266,0.0002361491,0.0002114752,0.0002141068,0.4290921,0.005429193,0.5033691,0.006994508,0.05222154],"study_design_scores_gemma":[0.00003051967,0.00006986642,0.0001800524,0.00006469831,0.00002776924,0.00005748343,0.00001400924,0.8781828,0.00203352,0.1177535,0.001552969,0.00003261365],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004082893,0.001191833,0.9890476,0.0005800566,0.0001411721,0.00008970398,0.00005851982,0.0003271977,0.004481118],"genre_scores_gemma":[0.327113,0.003853563,0.6539188,0.001453916,0.001261991,0.001004343,0.0005251176,0.001381698,0.009487546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01417885,"threshold_uncertainty_score":0.07498586,"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."}}