{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003173509,0.0003618457,0.0003528569,0.0006162476,0.0002007008,0.0001675571,0.001731197,0.0003191112,0.00001946708],"category_scores_gemma":[0.000269439,0.0004514311,0.0002422298,0.0008757169,0.00009565854,0.0002741865,0.0008795158,0.0002706864,0.00003176812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002400323,"about_ca_system_score_gemma":0.0002981939,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003127962,"about_ca_topic_score_gemma":0.000005310261,"domain_scores_codex":[0.9978727,0.00007517134,0.000269876,0.001244009,0.0001223673,0.0004159377],"domain_scores_gemma":[0.997484,0.0004558132,0.0003432513,0.001112624,0.0004486237,0.0001556514],"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":[0.0000159953,0.000046622,0.00005351257,0.00006033624,0.0000332558,0.000009992976,0.00004156051,0.9120533,0.000002422253,0.08724634,0.0004090987,0.00002748382],"study_design_scores_gemma":[0.000457381,0.00007695628,0.00002247895,0.0001011553,0.00004759997,6.053014e-7,0.00001296958,0.948696,0.0001378909,0.05001488,0.0000141315,0.0004179132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0002651332,0.00001505728,0.9952488,0.0001983552,0.0009548976,0.001082609,0.00006690186,0.002069277,0.00009898367],"genre_scores_gemma":[0.6055518,0.000009629121,0.3933153,0.00007257349,0.00005939768,0.00002695063,0.000217521,0.00005780447,0.0006889855],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6052867,"threshold_uncertainty_score":0.9997938,"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."}}