{"id":"W1814829895","doi":"10.1109/tsipn.2016.2620440","title":"Efficient Distributed Online Prediction and Stochastic Optimization With Approximate Distributed Averaging","year":2016,"lang":"en","type":"preprint","venue":"IEEE Transactions on Signal and Information Processing over Networks","topic":"Distributed Control Multi-Agent Systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Regret; Gossip; Scaling; Distributed algorithm; Computer science; Mathematics; Upper and lower bounds; Eigenvalues and eigenvectors; Random walk; Computation; Matrix (chemical analysis); Mathematical optimization; Combinatorics; Discrete mathematics; Algorithm; Distributed computing","routes":{"ca_aff":true,"ca_fund":true,"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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0002956004,0.0005055034,0.0004433026,0.000295581,0.0005596921,0.00109508,0.0003252627,0.0003404661,0.00001117297],"category_scores_gemma":[0.000007040942,0.0003948309,0.00007181247,0.0004455297,0.0001202713,0.001757627,0.00003130379,0.0006462157,0.000001933008],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002155062,"about_ca_system_score_gemma":0.0001629576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001009898,"about_ca_topic_score_gemma":0.000001450138,"domain_scores_codex":[0.9975474,0.00008381724,0.0008013055,0.0005609301,0.0005669522,0.0004396314],"domain_scores_gemma":[0.9982403,0.0000965502,0.0006829981,0.0003639005,0.0003950179,0.0002212534],"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":[0.0001173937,0.000089205,0.000008660837,0.0001881502,0.00007337642,0.000001268549,0.0002261046,0.9676604,0.000004320001,0.00008083671,0.00003404082,0.03151627],"study_design_scores_gemma":[0.001612716,0.0001068824,0.0002214027,0.001261268,0.0001030175,0.00003317621,0.0000426083,0.9960587,0.00002542561,0.00005104154,0.00004942291,0.0004343339],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001353786,0.0001378207,0.9948248,0.0002192767,0.0005007527,0.0008157638,0.001630914,0.0004834129,0.0000334267],"genre_scores_gemma":[0.9958118,0.00004164355,0.002798375,0.0001238965,0.00008848483,0.000154183,0.0009489254,0.00002133865,0.00001142093],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.994458,"threshold_uncertainty_score":0.9999419,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.008005984302644301,"score_gpt":0.2053340255659251,"score_spread":0.1973280412632809,"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."}}