{"id":"W4380993202","doi":"10.48550/arxiv.2306.08289","title":"$\\textbf{A}^2\\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University; Mila - Quebec Artificial Intelligence Institute","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Grand Équipement National De Calcul Intensif; Agence Nationale de la Recherche; Compute Canada","keywords":"Asynchronous communication; Gossip; Asynchrony (computer programming); Computer science; Synchronization (alternating current); Distributed computing; Momentum (technical analysis); Network topology; Process (computing); Scaling; Adaptation (eye); Topology (electrical circuits); Channel (broadcasting); Computer network; Mathematics; Engineering; Physics; Electrical engineering","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"],"consensus_categories":[],"category_scores_codex":[0.0006513535,0.0004182226,0.0004765685,0.0007453152,0.0003205198,0.0003239329,0.003003745,0.0004088603,0.00004247042],"category_scores_gemma":[0.0003214387,0.0005508478,0.0001778359,0.001474083,0.0001232201,0.0005976897,0.003446953,0.001231842,0.0001090839],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000636228,"about_ca_system_score_gemma":0.0001832319,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004653808,"about_ca_topic_score_gemma":0.0003446821,"domain_scores_codex":[0.9970432,0.0004838658,0.0004841799,0.001238287,0.0001693303,0.0005811497],"domain_scores_gemma":[0.9969831,0.0004206517,0.0005337049,0.001670799,0.0002296655,0.0001620651],"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":[0.00001258562,0.00007477411,0.006670943,0.00004680474,0.0000386557,0.00008925096,0.0009889171,0.8721679,0.00001154546,0.1175533,0.00006546672,0.002279939],"study_design_scores_gemma":[0.0005510642,0.0000418463,0.002802399,0.0002594526,0.00002502025,0.000003937012,0.0001210374,0.945261,0.00005648643,0.05031772,0.00005710296,0.0005029435],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03084917,0.0001520866,0.9646,0.0001546211,0.0003335811,0.0006335436,0.000002873272,0.002102297,0.001171782],"genre_scores_gemma":[0.9461773,0.0008208621,0.05239174,0.00005572757,0.00002287682,0.00001147916,0.00007084374,0.00004963994,0.0003995293],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9153281,"threshold_uncertainty_score":0.9996943,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1035355741640039,"score_gpt":0.2176154528292092,"score_spread":0.1140798786652053,"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."}}