{"id":"W4390905761","doi":"10.1109/icaicta59291.2023.10390158","title":"Enhancing Communication Efficiency in Adam Optimizer for Distributed Deep Learning","year":2023,"lang":"en","type":"article","venue":"","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Deep learning; Computer science; Overhead (engineering); Reduction (mathematics); Artificial intelligence; Distributed computing; Communications system; Models of communication; Computer network; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001795887,0.001052608,0.001090041,0.0003820046,0.0005276009,0.0008678491,0.001608784,0.0008362947,0.0035607],"category_scores_gemma":[0.006953887,0.000326195,0.0003961369,0.0004296905,0.0007862003,0.00219984,0.001403754,0.002108259,0.0007579355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007150233,"about_ca_system_score_gemma":0.0009790078,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009071183,"about_ca_topic_score_gemma":0.0009575029,"domain_scores_codex":[0.9985124,0.0005331727,0.00009341072,0.0002153738,0.000448774,0.0001967987],"domain_scores_gemma":[0.9974688,0.001448653,0.0001458023,0.0004778799,0.0003571824,0.0001016196],"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":[0.00142152,0.0003160671,0.001576995,0.0002340616,0.00008382048,0.000450509,0.0002404897,0.7042189,0.02054808,0.02613086,0.0101575,0.2346212],"study_design_scores_gemma":[0.00003479748,0.00009511284,0.0001072395,0.000007484222,0.00000723582,0.00004360093,0.00001838398,0.9896474,0.005961786,0.003144395,0.0009276342,0.000004868302],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08990718,0.001381953,0.8967065,0.001147168,0.0002867851,0.00009239717,0.00008754631,0.003588601,0.006801923],"genre_scores_gemma":[0.8592609,0.0004647765,0.1351677,0.0003135761,0.0001710125,0.0001654396,0.0001933045,0.000279281,0.003983877],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.0035607,"threshold_uncertainty_score":0.01191169,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02050733473298952,"score_gpt":0.2892274543532589,"score_spread":0.2687201196202693,"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."}}