{"id":"W2962684017","doi":"10.1109/infocom.2018.8486422","title":"Online Job Scheduling in Distributed Machine Learning Clusters","year":2018,"lang":"en","type":"article","venue":"","topic":"IoT and Edge/Fog Computing","field":"Computer Science","cited_by":117,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Server; Distributed computing; Testbed; Scheduling (production processes); Machine learning; Job shop scheduling; Artificial intelligence; Subroutine; Schedule; Job scheduler; Cloud computing; Scalability; Operating system; Computer network; Mathematical optimization","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":[0.0003374741,0.0001181846,0.000136909,0.0001254177,0.0001627428,0.0001215803,0.000554316,0.00005034729,0.000008774369],"category_scores_gemma":[0.0001008424,0.0001057663,0.0000369938,0.0005892245,0.00003930153,0.0002583424,0.0004764615,0.000262574,0.00008659763],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005007807,"about_ca_system_score_gemma":0.00003508138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001859368,"about_ca_topic_score_gemma":0.00008682706,"domain_scores_codex":[0.998877,0.00005923947,0.0002313032,0.0003108927,0.0001495363,0.0003720447],"domain_scores_gemma":[0.9994985,0.00007444328,0.0000521748,0.000240104,0.00006182226,0.00007292828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007795876,0.0008720703,0.4833815,0.0001073629,0.00009732094,0.0002392795,0.009700193,0.02347535,0.003913149,0.00981395,0.008396862,0.459925],"study_design_scores_gemma":[0.0003200944,0.00006594423,0.01110712,0.00003058699,0.000001200713,0.000008988,0.00002331581,0.9814189,0.0003113618,0.0002189066,0.00633917,0.0001544168],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3765806,0.00003638148,0.6187565,0.0008413785,0.002078035,0.00004725749,1.82243e-7,0.000233689,0.001425957],"genre_scores_gemma":[0.8986427,0.000002867431,0.09928015,0.0004131884,0.001300537,9.005226e-7,0.00001576022,0.00000919077,0.0003347412],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9579436,"threshold_uncertainty_score":0.4313023,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01878961325288999,"score_gpt":0.2598877140234045,"score_spread":0.2410981007705145,"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."}}