{"id":"W3035359320","doi":"10.48550/arxiv.2006.06587","title":"AdaS: Adaptive Scheduling of Stochastic Gradients","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Generalization; Artificial intelligence; Adaptive optimization; Stochastic gradient descent; Scheduling (production processes); Machine learning; Artificial neural network; Mathematical optimization; Algorithm; Mathematics","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":[0.001879283,0.001162263,0.001068247,0.0006355664,0.0005565337,0.001073376,0.001995985,0.001204348,0.004829589],"category_scores_gemma":[0.007412361,0.0006952016,0.0006951297,0.0005674011,0.00111172,0.001137156,0.001548713,0.002343192,0.002148403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001061553,"about_ca_system_score_gemma":0.002245396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003785526,"about_ca_topic_score_gemma":0.00492394,"domain_scores_codex":[0.99909,0.0003409002,0.00007708155,0.0001649901,0.0002454408,0.00008167946],"domain_scores_gemma":[0.9980505,0.0009246403,0.0001868489,0.000266545,0.0004213684,0.0001501876],"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":[0.0003902296,0.000165696,0.001233438,0.0001800347,0.00008696808,0.00009442466,0.0001445693,0.689387,0.005721435,0.03755279,0.01294371,0.2520998],"study_design_scores_gemma":[0.00003301849,0.00003568571,0.00005322898,0.000007630987,0.00000383052,0.00001346138,0.000005867477,0.9906735,0.001299911,0.006350439,0.001517581,0.000005782904],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00475242,0.0001276884,0.9918995,0.0001478819,0.0001047456,0.00007431959,0.00005166287,0.001681124,0.001160581],"genre_scores_gemma":[0.2428815,0.0002304449,0.7496128,0.0003788423,0.0001521303,0.0005501381,0.0004013961,0.0009127519,0.004880038],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004829589,"threshold_uncertainty_score":0.01615655,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09942448309067382,"score_gpt":0.1981458448133284,"score_spread":0.09872136172265454,"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."}}