{"id":"W4401035172","doi":"10.5802/ojmo.31","title":"Tight analyses for subgradient descent I: Lower bounds","year":2024,"lang":"lv","type":"article","venue":"Open Journal of Mathematical Optimization","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Subgradient method; Mathematics; Lipschitz continuity; Upper and lower bounds; Differentiable function; Combinatorics; Convex function; Descent (aeronautics); Matching (statistics); Regular polygon; Function (biology); Discrete mathematics; Mathematical optimization; Pure mathematics; Statistics; 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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002033846,0.0002616321,0.0005849719,0.0002629956,0.0002198862,0.003443709,0.001319716,0.0001111213,0.0006728694],"category_scores_gemma":[0.0004887787,0.000188665,0.0003746969,0.0006021521,0.00007015027,0.001145197,0.0002856299,0.0003829402,0.00006297145],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001289136,"about_ca_system_score_gemma":0.0003390179,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003535881,"about_ca_topic_score_gemma":3.819471e-7,"domain_scores_codex":[0.9974573,0.0001907051,0.00108468,0.0003431875,0.0005781215,0.0003459727],"domain_scores_gemma":[0.9979324,0.0005336941,0.000469078,0.0003317928,0.0004640557,0.0002689423],"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":[0.0001758713,0.001359176,0.00001246008,0.001184139,0.0007612627,0.0002877372,0.003267007,0.7736562,0.00009679452,0.1365721,0.01736605,0.06526125],"study_design_scores_gemma":[0.0005355274,0.0007735094,0.000005997278,0.001509028,0.0002585387,0.0002328595,0.00003886286,0.9756187,0.0001449695,0.01022397,0.01043056,0.0002274508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002773088,0.00181308,0.9889627,0.004538109,0.001717608,0.0004099009,0.000006910527,0.00002613028,0.002248235],"genre_scores_gemma":[0.06325282,0.0002616681,0.9304822,0.0001792038,0.0006727988,0.00001246775,0.00000814654,0.00005247862,0.005078234],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2019625,"threshold_uncertainty_score":0.9975908,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06688709976136888,"score_gpt":0.3818794323535867,"score_spread":0.3149923325922179,"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."}}