{"id":"W2963179285","doi":"","title":"A Modular Analysis of Adaptive (Non-)Convex Optimization: Optimism, Composite Objectives, and Variational Bounds.","year":2017,"lang":"en","type":"article","venue":"Spiral (Imperial College London)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Mathematical proof; Regret; Computer science; Mathematical optimization; Generalization; Modular design; Convex analysis; Gradient descent; Convex optimization; Regular polygon; Theoretical computer science; Mathematics; Artificial intelligence; Machine learning; Artificial neural network","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003525995,0.0003001361,0.000669907,0.0005570293,0.0007199773,0.0004009672,0.001139557,0.0001601669,0.00006047647],"category_scores_gemma":[0.0001615177,0.0003104774,0.0002007223,0.0008361728,0.0003406583,0.001107935,0.0006030324,0.0001368289,0.000002400147],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009728806,"about_ca_system_score_gemma":0.0002016711,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001786243,"about_ca_topic_score_gemma":0.00001468141,"domain_scores_codex":[0.9978517,0.0000921281,0.0005372819,0.000696923,0.0004972941,0.0003247122],"domain_scores_gemma":[0.9975712,0.0001049496,0.0006174401,0.001054518,0.0004861853,0.0001657205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003738435,0.0002769722,0.00211085,0.00002869359,0.001662111,0.00003487964,0.001396935,0.3695666,0.002144225,0.6215463,0.0001694885,0.0006890717],"study_design_scores_gemma":[0.001271925,0.0003537571,0.01127293,0.00002494845,0.0002778052,0.000008800296,0.00002522171,0.9820232,0.001109943,0.003251538,0.00003612434,0.0003438211],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01588836,0.00007968437,0.9793628,0.0002589996,0.000473758,0.0005970552,0.0001425726,0.0001427183,0.003054007],"genre_scores_gemma":[0.6369246,0.00001730871,0.3627191,0.00008340989,0.00007783783,0.00004777679,0.00002644932,0.00001471071,0.00008876545],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6210363,"threshold_uncertainty_score":0.9999347,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01233699994632156,"score_gpt":0.2446377531609609,"score_spread":0.2323007532146393,"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."}}