{"id":"W4321012054","doi":"10.48550/arxiv.2302.06763","title":"Breaking the Lower Bound with (Little) Structure: Acceleration in Non-Convex Stochastic Optimization with Heavy-Tailed Noise","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"York University; National Science Foundation","keywords":"Bounded function; Mathematics; Upper and lower bounds; Combinatorics; Omega; Convex function; Rate of convergence; Regular polygon; Discrete mathematics; Physics; Mathematical analysis; Quantum mechanics; Computer science; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003178156,0.002044475,0.001898822,0.0007478438,0.0006909338,0.001664603,0.00183322,0.00183605,0.002936239],"category_scores_gemma":[0.01608845,0.0006392764,0.001159551,0.0008436012,0.002642245,0.003075801,0.003506093,0.004554929,0.001011952],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001154256,"about_ca_system_score_gemma":0.001581072,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003472751,"about_ca_topic_score_gemma":0.002321546,"domain_scores_codex":[0.9985098,0.0005119905,0.00004344948,0.0002718004,0.0004570366,0.0002058246],"domain_scores_gemma":[0.9937224,0.004495421,0.0003338963,0.0006877003,0.0004889859,0.0002715104],"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":[0.0002302215,0.0001332403,0.001001935,0.0002410352,0.00006682718,0.0001924042,0.0002117149,0.7858617,0.004722561,0.154815,0.005120587,0.04740284],"study_design_scores_gemma":[0.000008740593,0.00003201564,0.0000597982,0.00001077797,0.000003965356,0.0000126264,0.000005146216,0.9782606,0.0004406752,0.02071328,0.0004466784,0.000005683432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01343326,0.0006539791,0.9802343,0.0009673351,0.0001432759,0.00004404105,0.00004925567,0.0003316943,0.004142869],"genre_scores_gemma":[0.6182263,0.001699946,0.3647105,0.001835166,0.0006247592,0.0003748289,0.000304129,0.0006185344,0.01160579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003472751,"threshold_uncertainty_score":0.01680785,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03945059861527851,"score_gpt":0.1882352903061463,"score_spread":0.1487846916908678,"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."}}