{"id":"W3208237615","doi":"10.48550/arxiv.2110.15412","title":"Stochastic Mirror Descent: Convergence Analysis and Adaptive Variants via the Mirror Stochastic Polyak Stepsize","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Stochastic gradient descent; Bounded function; Convergence (economics); Adaptive stepsize; Regular polygon; Mathematical optimization; Descent (aeronautics); Mathematics; Convex function; Stochastic optimization; Computer science; Gradient descent; Applied mathematics; Artificial intelligence; Numerical analysis; Mathematical analysis; Artificial neural network; Physics; Geometry","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":[0.002378926,0.0009623702,0.001120542,0.0007638984,0.0004102401,0.00100662,0.001469092,0.001049315,0.002713441],"category_scores_gemma":[0.008951422,0.0004204245,0.0007968856,0.0006603927,0.001848932,0.001632972,0.002102481,0.002004822,0.0006531295],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008159621,"about_ca_system_score_gemma":0.001359754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00203269,"about_ca_topic_score_gemma":0.001919377,"domain_scores_codex":[0.9990848,0.0003725099,0.00005069158,0.000165545,0.0002561565,0.00007017569],"domain_scores_gemma":[0.9971269,0.001717796,0.0001996216,0.0004050243,0.0004035299,0.0001471915],"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":[0.0002355558,0.000130609,0.002129436,0.0002014848,0.0001076009,0.0001702457,0.0001283826,0.7003689,0.006593966,0.2065723,0.002581874,0.08077972],"study_design_scores_gemma":[0.000008987123,0.00003955643,0.00007425614,0.000006482034,0.000003346774,0.00001245091,0.000004650339,0.982491,0.0006508459,0.01636418,0.0003383228,0.00000595188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01195115,0.0001777331,0.9859855,0.0002047995,0.00003822794,0.00004002278,0.00003013407,0.0001610488,0.001411497],"genre_scores_gemma":[0.5350877,0.0005007953,0.4567768,0.000279738,0.0001056736,0.0003682871,0.0002117104,0.0002832998,0.006385949],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.002713441,"threshold_uncertainty_score":0.01258111,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05651900974294029,"score_gpt":0.1963108193767179,"score_spread":0.1397918096337776,"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."}}