{"id":"W4320712010","doi":"10.48550/arxiv.2302.02607","title":"Target-based Surrogates for Stochastic Optimization","year":2023,"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; Canadian Institute for Advanced Research","keywords":"Stochastic gradient descent; Mathematical optimization; Computer science; Stochastic optimization; Optimization problem; Convergence (economics); Mathematics; Artificial intelligence","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":[0.003269933,0.001426759,0.001405591,0.0007013505,0.00053385,0.001622478,0.001421101,0.002024879,0.003989941],"category_scores_gemma":[0.01176392,0.0006866101,0.001089505,0.0007871887,0.001983359,0.00231745,0.002418995,0.003281526,0.001092626],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00135975,"about_ca_system_score_gemma":0.001675944,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001253714,"about_ca_topic_score_gemma":0.001340146,"domain_scores_codex":[0.9985159,0.0007237329,0.00006448998,0.0002208259,0.0003873845,0.00008765386],"domain_scores_gemma":[0.9961967,0.00246545,0.0003327061,0.000443051,0.0004208628,0.000141186],"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":[0.00005146562,0.00004745129,0.0003617091,0.0001023156,0.00003357985,0.00005187862,0.00004687875,0.8528855,0.00132952,0.1248693,0.001822682,0.01839777],"study_design_scores_gemma":[0.00000437834,0.00002016806,0.00002444419,0.000009320144,0.000002444324,0.00001156941,0.000003248153,0.9694141,0.0004337094,0.02942786,0.0006446238,0.000004072268],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002220012,0.00009499366,0.9957721,0.0001963854,0.00002343973,0.00001821443,0.00002627845,0.0001310724,0.001517635],"genre_scores_gemma":[0.4300338,0.0005701862,0.5590081,0.0004569915,0.000158419,0.0004342187,0.0003796897,0.0006574508,0.00830121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003989941,"threshold_uncertainty_score":0.01729333,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1002730716856377,"score_gpt":0.2058429616568232,"score_spread":0.1055698899711855,"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."}}