{"id":"W2985478892","doi":"10.1016/j.tcs.2019.11.015","title":"A modular analysis of adaptive (non-)convex optimization: Optimism, composite objectives, variance reduction, and variational bounds","year":2019,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"University of Alberta; Engineering and Physical Sciences Research Council; Alberta Machine Intelligence Institute","keywords":"Mathematical proof; Mathematical optimization; Regret; Computer science; Generalization; Convex optimization; Modular design; Mathematics; Convex analysis; Regular polygon; Algorithm; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.004059894,0.001331841,0.001023852,0.001302729,0.0004047407,0.001440145,0.001683747,0.001008707,0.003228386],"category_scores_gemma":[0.009301642,0.0006996695,0.001865484,0.0009785425,0.002399025,0.003227716,0.003262846,0.002851885,0.0003756862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001022649,"about_ca_system_score_gemma":0.0008557983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008515785,"about_ca_topic_score_gemma":0.0008564428,"domain_scores_codex":[0.998634,0.0007107439,0.00004212888,0.000199751,0.0003136525,0.00009961218],"domain_scores_gemma":[0.9971208,0.001786009,0.0002745553,0.0003130294,0.0003608096,0.0001448499],"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":[0.00003757511,0.00003808237,0.0003809881,0.0001179551,0.00009419565,0.00004474253,0.00009121366,0.1548637,0.002866973,0.8174424,0.001336711,0.02268557],"study_design_scores_gemma":[0.00000650022,0.00003121627,0.0002548926,0.00001952734,0.00002285598,0.00002076121,0.00001144754,0.6532216,0.0004251869,0.3451753,0.0007995201,0.00001113902],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007217158,0.0003797577,0.9887876,0.0003470323,0.00003713594,0.00001232639,0.00002248627,0.0000260132,0.003170523],"genre_scores_gemma":[0.6341818,0.001841101,0.3494898,0.0003828305,0.0006987434,0.0002142201,0.0001347162,0.000295007,0.01276172],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004059894,"threshold_uncertainty_score":0.02147102,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02138338947300127,"score_gpt":0.3353639411161184,"score_spread":0.3139805516431172,"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."}}