{"id":"W3037667206","doi":"","title":"DAve-QN: A Distributed Averaged Quasi-Newton Method with Local Superlinear Convergence Rate","year":2020,"lang":"en","type":"article","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Asynchronous communication; Hessian matrix; Bounded function; Convergence (economics); Computer science; Distributed algorithm; Computation; Rate of convergence; Mathematical optimization; Dimension (graph theory); Empirical risk minimization; Node (physics); Algorithm; Mathematics; Applied mathematics; Distributed computing; Channel (broadcasting)","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","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.001325327,0.0003221357,0.0005743398,0.002119347,0.002517514,0.00008807715,0.003499119,0.0003257792,0.000004443685],"category_scores_gemma":[0.0003715344,0.0003589617,0.00004869822,0.01090055,0.0281979,0.001416446,0.001943979,0.0005283057,0.000002045355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002311199,"about_ca_system_score_gemma":0.001089855,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002825732,"about_ca_topic_score_gemma":0.00002202191,"domain_scores_codex":[0.9965199,0.00006067187,0.0002968875,0.001509519,0.0009191213,0.0006939297],"domain_scores_gemma":[0.9962059,0.0001036286,0.000511598,0.000815008,0.00206401,0.0002998637],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003656803,0.0005314654,0.05355564,0.000358653,0.000227861,0.001407678,0.01107937,0.001139762,0.6088151,0.2745172,0.0003449649,0.04765658],"study_design_scores_gemma":[0.003932249,0.004323852,0.004445923,0.0008758938,0.0002797251,0.001175617,0.05647768,0.5156771,0.4019674,0.004815874,0.004037037,0.001991634],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3888105,0.00008305809,0.6041934,0.005597445,0.00008935527,0.0002928676,0.000007593245,0.0007110132,0.0002146666],"genre_scores_gemma":[0.8975465,0.0001012196,0.1022376,0.00006059089,0.00000580042,2.915343e-7,0.000001132917,0.000008025729,0.0000389454],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5145373,"threshold_uncertainty_score":0.9998862,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007380128414547346,"score_gpt":0.1899066916349073,"score_spread":0.18252656322036,"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."}}