{"id":"W2951536758","doi":"10.48550/arxiv.1810.02976","title":"Anytime Stochastic Gradient Descent: A Time to Hear from all the Workers","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Stochastic gradient descent; Exploit; Computation; Node (physics); Convergence (economics); Focus (optics); Set (abstract data type); Distributed computing; Algorithm; Artificial intelligence; Computer security","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":[0.002034798,0.001412512,0.001230148,0.0003372049,0.0009682628,0.001314237,0.002623219,0.001579627,0.004718954],"category_scores_gemma":[0.005925446,0.0007167704,0.0006312281,0.0006719637,0.001432054,0.002219138,0.002352507,0.002538649,0.001966722],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008137061,"about_ca_system_score_gemma":0.003085319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00394187,"about_ca_topic_score_gemma":0.006628501,"domain_scores_codex":[0.9985635,0.0004519288,0.00004970229,0.0002926276,0.0004758766,0.0001662764],"domain_scores_gemma":[0.9982281,0.0007106285,0.000148876,0.0004472342,0.0002811211,0.0001840596],"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":[0.001009445,0.0002752924,0.001802532,0.0002961904,0.00020429,0.0003795334,0.000630762,0.5678641,0.01642658,0.07441331,0.01892497,0.3177731],"study_design_scores_gemma":[0.00007562286,0.00007867697,0.00013021,0.00001369431,0.0000217921,0.00004130188,0.00005574538,0.9655411,0.002909184,0.02574982,0.005368871,0.00001409691],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004899532,0.0001924487,0.9913813,0.0004913806,0.0001107255,0.0000330779,0.00001762866,0.0009161243,0.001957777],"genre_scores_gemma":[0.2518384,0.0003656046,0.7353408,0.0006798044,0.0002758181,0.0002496978,0.0001752008,0.0006503972,0.01042416],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.004718954,"threshold_uncertainty_score":0.01578647,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05485075728300471,"score_gpt":0.1879363968906219,"score_spread":0.1330856396076172,"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."}}