{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003231444,0.0004767909,0.0003995799,0.0003675591,0.0002454949,0.0002588319,0.003731106,0.0002711957,0.0002179352],"category_scores_gemma":[0.0001082456,0.0004504811,0.0002383364,0.000915942,0.0002305372,0.0002288197,0.003525157,0.0005087472,0.001655207],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004404942,"about_ca_system_score_gemma":0.0001864699,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003113874,"about_ca_topic_score_gemma":0.0000137494,"domain_scores_codex":[0.9971448,0.0001876271,0.0002947549,0.001561958,0.000222087,0.000588783],"domain_scores_gemma":[0.9965333,0.0002475618,0.000279523,0.002308299,0.0002521775,0.0003790863],"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":[0.0001343969,0.0002900647,0.0002652176,0.0000236973,0.0004600467,0.0001551102,0.002567146,0.9328105,0.0000597306,0.03265313,0.02981939,0.0007615144],"study_design_scores_gemma":[0.0003305824,0.000175322,0.0004226317,0.0002530183,0.0001313359,0.000005177039,0.00003947232,0.9591476,0.00008836849,0.03789522,0.0008057802,0.000705428],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02067821,0.00003582644,0.975444,0.0006489126,0.0005890849,0.001034932,0.00004116135,0.0007711449,0.0007567091],"genre_scores_gemma":[0.9514287,0.00001138497,0.04494963,0.0009119615,0.0001971098,0.00001260022,0.00004760013,0.00005849287,0.002382525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9307505,"threshold_uncertainty_score":0.9997947,"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."}}