{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001089044,0.0007153473,0.0006501262,0.0003134018,0.0005209722,0.0006782655,0.001662647,0.0007708362,0.003680954],"category_scores_gemma":[0.004357188,0.0003076422,0.0002836072,0.0003681752,0.0006724144,0.001400514,0.001316116,0.001572173,0.001255189],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007942395,"about_ca_system_score_gemma":0.001409246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003621613,"about_ca_topic_score_gemma":0.007406028,"domain_scores_codex":[0.9994061,0.0001736948,0.00002096375,0.000147861,0.0001877499,0.00006367264],"domain_scores_gemma":[0.9988752,0.0004701828,0.0001014433,0.0002761967,0.00016293,0.0001140985],"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":[0.0005343401,0.0002397993,0.001339542,0.0001491758,0.00006494201,0.0001504907,0.0001416975,0.6947159,0.01934046,0.04096556,0.020029,0.2223292],"study_design_scores_gemma":[0.00003408118,0.00002722865,0.00009833383,0.000003184616,0.000004175907,0.00001334306,0.00000633014,0.9900157,0.002051416,0.006580789,0.001160986,0.0000044279],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02621408,0.0002339885,0.9644907,0.0006155016,0.0001319444,0.00005716848,0.00009563625,0.004480409,0.003680438],"genre_scores_gemma":[0.6517891,0.0002407048,0.3390587,0.0003977459,0.0001843043,0.0002510776,0.0003298077,0.0007315346,0.007016991],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003680954,"threshold_uncertainty_score":0.01231396,"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."}}