{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01309201,0.005197703,0.0038091,0.003793293,0.002309878,0.006540563,0.004728997,0.004373198,0.01812928],"category_scores_gemma":[0.07342727,0.002066783,0.003649207,0.003408018,0.00484079,0.009240924,0.006694598,0.01344694,0.003847111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007807654,"about_ca_system_score_gemma":0.005496039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009993123,"about_ca_topic_score_gemma":0.008642033,"domain_scores_codex":[0.9919004,0.003036502,0.0002512583,0.001085271,0.002450709,0.001275864],"domain_scores_gemma":[0.968591,0.02251481,0.001518669,0.002598161,0.003277055,0.001500385],"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":[0.0006114452,0.0003389104,0.002163578,0.001042491,0.0002733266,0.0003406517,0.0004334284,0.2617403,0.001968097,0.6321509,0.04424894,0.05468804],"study_design_scores_gemma":[0.00004879634,0.0001244411,0.0004680329,0.0003324039,0.00008559354,0.00008518052,0.00008307617,0.6955363,0.0009709148,0.2931014,0.009127178,0.00003660691],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01052404,0.00621964,0.9276456,0.005266356,0.0006227599,0.0001808902,0.0006400722,0.001148711,0.04775198],"genre_scores_gemma":[0.4947587,0.01017427,0.4181466,0.00679127,0.00230069,0.002057885,0.003187758,0.004639428,0.05794335],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01812928,"threshold_uncertainty_score":0.06923801,"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."}}