{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000286515,0.00007640117,0.00009512104,0.00008809542,0.0002150395,0.00004858218,0.0006640129,0.00003299599,0.000004565883],"category_scores_gemma":[0.0001248037,0.00007554199,0.00003134201,0.001327,0.00002135886,0.0002580273,0.0002696242,0.0001282824,0.00005254956],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004576513,"about_ca_system_score_gemma":0.00001361261,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007754524,"about_ca_topic_score_gemma":0.00005981091,"domain_scores_codex":[0.999127,0.00004424344,0.0002087687,0.0002574451,0.00009614688,0.0002664394],"domain_scores_gemma":[0.9988053,0.0005758476,0.00006294161,0.0004660678,0.0000507246,0.00003905773],"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":[0.000006260217,0.00005699352,0.0003439656,0.00001159605,0.0000038677,0.00000132132,0.0005813373,0.8525853,0.004117352,0.09121376,0.0004418591,0.05063642],"study_design_scores_gemma":[0.000245728,0.00002022706,0.001088384,0.00001114199,0.00000109618,0.000001024974,0.00007699964,0.9884259,0.002412655,0.004287209,0.003320597,0.0001090849],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005829676,0.00005774611,0.9915667,0.001311439,0.00003350916,0.0003285619,9.196485e-7,0.0005296724,0.0003417806],"genre_scores_gemma":[0.7710211,0.0000809847,0.2280829,0.00009911217,0.00001455878,0.0002901855,0.00006241827,0.000009878611,0.0003387936],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7651914,"threshold_uncertainty_score":0.3080513,"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."}}