{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00193131,0.001000146,0.001182729,0.0004381293,0.001269082,0.001303041,0.002461118,0.000759016,0.002811811],"category_scores_gemma":[0.003698253,0.0005675358,0.0004026566,0.0008363844,0.0007927804,0.001189264,0.001395489,0.0008605767,0.0006291542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001541828,"about_ca_system_score_gemma":0.003230018,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006402435,"about_ca_topic_score_gemma":0.006348699,"domain_scores_codex":[0.9987181,0.0003121718,0.00005695746,0.0003563369,0.0002102948,0.0003461936],"domain_scores_gemma":[0.9975432,0.00110885,0.0001974693,0.0004313483,0.0003275378,0.0003915819],"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":[0.000550776,0.0002109743,0.001037892,0.00009082047,0.0000229627,0.0000985657,0.0000925803,0.9410751,0.003483122,0.0066465,0.002916034,0.04377466],"study_design_scores_gemma":[0.00002741626,0.00003011317,0.00009241091,0.000001958258,0.000002987442,0.00001006249,0.0000216749,0.9953049,0.00077842,0.00338912,0.0003372081,0.000003690828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1781301,0.0005982328,0.8092986,0.0005682563,0.0001824266,0.000317452,0.000181947,0.003448676,0.00727425],"genre_scores_gemma":[0.8744534,0.0001112214,0.1222254,0.00008926456,0.00003992398,0.000152704,0.0001670233,0.0001984766,0.002562575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006402435,"threshold_uncertainty_score":0.01273036,"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."}}