{"id":"W3105249545","doi":"","title":"Winning the Lottery with Continuous Sparsification","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Pruning; Ticket; Heuristic; Regularization (linguistics); Machine learning; Artificial intelligence; Lottery; Artificial neural network; Heuristics; Deep neural networks; 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":[0.001799773,0.001265159,0.001468877,0.0007287265,0.0006179234,0.00147708,0.002158983,0.001903237,0.005613645],"category_scores_gemma":[0.009188274,0.0008187703,0.001011093,0.0007153238,0.002044179,0.004251447,0.002574486,0.003015324,0.001429836],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009827637,"about_ca_system_score_gemma":0.001232326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001975462,"about_ca_topic_score_gemma":0.003814289,"domain_scores_codex":[0.9992737,0.0002559329,0.00003649135,0.0001753504,0.0001569513,0.0001016079],"domain_scores_gemma":[0.9967489,0.002001382,0.0002544843,0.000675128,0.000166072,0.0001538976],"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":[0.0005806473,0.0002562908,0.003022031,0.0002887573,0.0001748271,0.0002888897,0.000210813,0.6944798,0.004223427,0.07653167,0.01469157,0.2052512],"study_design_scores_gemma":[0.00003818729,0.00005944807,0.0001059559,0.00002561405,0.00001563178,0.00005619939,0.00002620387,0.9524876,0.001095388,0.0448654,0.001216056,0.000008349932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08918773,0.001203254,0.8954189,0.001669211,0.0001746801,0.0001385007,0.0002993087,0.002386958,0.009521349],"genre_scores_gemma":[0.7152312,0.0005322874,0.2751314,0.0009837574,0.0001925394,0.0003133988,0.0008913822,0.0005297484,0.006194314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005613645,"threshold_uncertainty_score":0.01877958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07439868089584833,"score_gpt":0.1690443046071115,"score_spread":0.0946456237112632,"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."}}