{"id":"W3080910898","doi":"10.48550/arxiv.2008.10898","title":"PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Simple (philosophy); Estimator; Probabilistic logic; Mathematical optimization; Applied mathematics; Mathematics; Computer science; Algorithm; Artificial intelligence; Statistics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002786431,0.001821609,0.00241676,0.0007351507,0.0005673414,0.00158565,0.002807813,0.002053068,0.003722547],"category_scores_gemma":[0.01268249,0.001144743,0.000965892,0.0008591712,0.001709657,0.003132776,0.002487594,0.003520426,0.00180299],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009223849,"about_ca_system_score_gemma":0.002843503,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002559687,"about_ca_topic_score_gemma":0.003170655,"domain_scores_codex":[0.9982467,0.0007282736,0.00007524826,0.0002919738,0.0005126,0.0001453005],"domain_scores_gemma":[0.9969991,0.001786706,0.0002009726,0.00034661,0.0005104077,0.0001562021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002947648,0.0001704033,0.001319778,0.0004791271,0.0001857635,0.0001675708,0.00007099604,0.7191588,0.005219581,0.08457777,0.01450778,0.1738478],"study_design_scores_gemma":[0.00002404781,0.00003201001,0.00006893391,0.00001295025,0.000008232282,0.00003112967,0.000003691337,0.9877144,0.0007068454,0.01015381,0.001230645,0.00001336485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001331222,0.0002561188,0.9970267,0.0001525934,0.00005585744,0.0000464776,0.0000348783,0.0005007456,0.0005953864],"genre_scores_gemma":[0.1598867,0.0009614016,0.8314437,0.0008298928,0.0003020928,0.0005879924,0.0005547954,0.0007748823,0.004658615],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003722547,"threshold_uncertainty_score":0.01473624,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07104277370489873,"score_gpt":0.2059147819171644,"score_spread":0.1348720082122656,"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."}}