{"id":"W4287685829","doi":"10.48550/arxiv.2008.10526","title":"Stochastic Multi-level Composition Optimization Algorithms with Level-Independent Convergence Rates","year":2020,"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":"Natural Sciences and Engineering Research Council of Canada; University of California, Davis","keywords":"Oracle; Convergence (economics); Generalization; Mathematics; Algorithm; Function (biology); Sample (material); Composition (language); Stochastic optimization; Mathematical optimization; Stochastic approximation; Applied mathematics; Order (exchange); Computer science; Mathematical analysis","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001812697,0.0005434534,0.0004709667,0.0003800938,0.0002712934,0.0002317995,0.001871857,0.0003216928,0.00004469829],"category_scores_gemma":[0.00004495219,0.0006052713,0.0001411513,0.000960857,0.0001752495,0.0006226808,0.001470815,0.0006144514,0.00004570901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003670242,"about_ca_system_score_gemma":0.000326628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009489372,"about_ca_topic_score_gemma":0.00001208889,"domain_scores_codex":[0.9971354,0.0001538089,0.0003505294,0.001655874,0.0002839656,0.0004204453],"domain_scores_gemma":[0.9974377,0.0001119632,0.0005294221,0.001040662,0.0005794549,0.0003008536],"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":[0.0000410562,0.0001239912,0.0001207513,0.00004565063,0.00008995071,0.0001228178,0.0002518699,0.9676013,0.00003848015,0.0313587,0.00006121528,0.0001442157],"study_design_scores_gemma":[0.0008842803,0.0001512166,0.0005030612,0.0001830071,0.0000953345,0.00001636633,0.00004896991,0.9938293,0.0004903497,0.00310726,0.000002077833,0.0006888406],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001355535,0.00002428204,0.9958882,0.0001937784,0.0005258116,0.0009470608,0.00009950042,0.0008851212,0.00008072287],"genre_scores_gemma":[0.6514274,0.00002930725,0.3480909,0.00009595503,0.00003478074,0.000007746949,0.0001254005,0.00003221773,0.0001563087],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6500719,"threshold_uncertainty_score":0.9996399,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1600929566306903,"score_gpt":0.2231963214143554,"score_spread":0.0631033647836651,"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."}}