{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005918858,0.001932601,0.002460231,0.0009934613,0.0007810061,0.001852758,0.002602259,0.002539718,0.003880025],"category_scores_gemma":[0.01911206,0.001245583,0.001707738,0.001031908,0.002287881,0.003554679,0.004340898,0.0050162,0.001449597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001760046,"about_ca_system_score_gemma":0.002146551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002505622,"about_ca_topic_score_gemma":0.002117345,"domain_scores_codex":[0.9975254,0.0009936423,0.0001182712,0.0004817327,0.0006329506,0.0002479571],"domain_scores_gemma":[0.9918268,0.005751173,0.000661847,0.000651637,0.0007435203,0.0003650444],"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":[0.0002621037,0.000144747,0.001141281,0.0002433393,0.0000996805,0.00007637531,0.000119563,0.8686018,0.002220662,0.07868553,0.0014631,0.04694182],"study_design_scores_gemma":[0.000009681774,0.00001791871,0.00003125744,0.000005610926,0.000004127066,0.000006493734,0.00000349146,0.9905773,0.0003577216,0.008791177,0.0001917435,0.00000344635],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004306163,0.0001591871,0.9942238,0.0001457282,0.00001956981,0.00004068022,0.00001736784,0.0002913156,0.0007961184],"genre_scores_gemma":[0.2007987,0.0002905701,0.7929041,0.0003196631,0.0001023672,0.0004615265,0.0002177528,0.000469138,0.004436101],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005918858,"threshold_uncertainty_score":0.03130227,"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."}}