{"id":"W3035688841","doi":"","title":"Acceleration for Compressed Gradient Descent in Distributed Optimization","year":2020,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Acceleration; Descent (aeronautics); Computer science; Gradient descent; Mathematical optimization; Mathematics; Artificial intelligence; Physics; Aerospace engineering; Engineering; Classical mechanics","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":[],"consensus_categories":[],"category_scores_codex":[0.00004412485,0.0001050787,0.0001036379,0.00006840677,0.00003504465,0.00007443003,0.0001362999,0.00003880449,0.00008503739],"category_scores_gemma":[0.00007694402,0.0001116425,0.00003056402,0.00007289604,0.000008868508,0.0000880161,0.00002059838,0.0001996015,0.000004934659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005787924,"about_ca_system_score_gemma":0.000007634398,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001525187,"about_ca_topic_score_gemma":0.000008274474,"domain_scores_codex":[0.9994327,0.0000239342,0.0001681927,0.0001472999,0.0001204037,0.000107407],"domain_scores_gemma":[0.9997497,0.00003384583,0.00003929492,0.00004960863,0.00008916731,0.00003841633],"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":[0.00005051926,0.00001549302,0.0008717011,0.000006097113,0.0000132371,0.000002484039,0.0001252482,0.987586,0.00507065,0.003572378,0.0001860325,0.002500109],"study_design_scores_gemma":[0.0003753522,0.00006644394,0.0005197123,0.00005240599,0.000002983808,6.96039e-7,0.00002080631,0.9917306,0.00496134,0.0002122732,0.001946665,0.0001107672],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03028551,0.00002588212,0.9647868,0.001717506,0.0001852086,0.0002427265,0.00003128708,0.0004587295,0.00226633],"genre_scores_gemma":[0.9949061,0.00004745667,0.004315677,0.000154291,0.00007004766,0.00002552449,0.0004544523,0.00001678083,0.000009628919],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9646206,"threshold_uncertainty_score":0.455265,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06559826797288805,"score_gpt":0.2811279469838047,"score_spread":0.2155296790109167,"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."}}