{"id":"W2894459442","doi":"10.48550/arxiv.1809.09354","title":"Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Coordinate descent; Lipschitz continuity; Empirical risk minimization; Mathematics; Stochastic gradient descent; Sampling (signal processing); Minification; Gradient descent; Mathematical optimization; Computer science; Combinatorics; Applied mathematics; Algorithm; Artificial intelligence; Pure 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":[0.005453681,0.001753021,0.002642307,0.0008288192,0.0009885799,0.00166396,0.003188666,0.002200039,0.004742111],"category_scores_gemma":[0.02818595,0.001084902,0.001261906,0.0007009449,0.002426285,0.002862155,0.002507159,0.00423293,0.002270566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001887856,"about_ca_system_score_gemma":0.003208227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00336575,"about_ca_topic_score_gemma":0.003555415,"domain_scores_codex":[0.9969621,0.001348588,0.0001338645,0.0005552298,0.0006749325,0.0003252285],"domain_scores_gemma":[0.9893171,0.006006966,0.0005814544,0.001469181,0.002030728,0.0005945213],"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":[0.0009242722,0.0003118364,0.002640695,0.0004082916,0.0001255433,0.0001818164,0.0002214459,0.7539983,0.004026427,0.09644638,0.01634433,0.1243707],"study_design_scores_gemma":[0.00003835568,0.00008082489,0.0001461968,0.00002054463,0.00001131811,0.00002770683,0.000008671564,0.9857318,0.001092749,0.01180476,0.001026636,0.00001037991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01624511,0.001237071,0.9770006,0.0005713459,0.0002006639,0.0001597687,0.00008064025,0.001616925,0.002887946],"genre_scores_gemma":[0.440179,0.0008609704,0.5473875,0.0009196844,0.0003555797,0.000910126,0.0006457423,0.0008437803,0.007897537],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.005453681,"threshold_uncertainty_score":0.02884215,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1541591001487066,"score_gpt":0.2405477677765443,"score_spread":0.08638866762783776,"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."}}