{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004205376,0.00008744788,0.00007658172,0.00002053753,0.000191337,0.0000430652,0.0008212749,0.00002161069,0.000005882145],"category_scores_gemma":[0.000008772305,0.00006917442,0.00002760495,0.0008666374,0.00007962342,0.0003855873,0.0001436788,0.0001235537,0.00009774376],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002260233,"about_ca_system_score_gemma":0.00002021982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004396316,"about_ca_topic_score_gemma":0.000003276632,"domain_scores_codex":[0.9993044,0.0000358922,0.00006712521,0.0003872956,0.00004588126,0.0001594548],"domain_scores_gemma":[0.9992407,0.00008383895,0.00008291296,0.0004595707,0.00005012453,0.00008287649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004428563,0.00003867885,0.007983551,0.000006474314,0.0000308567,0.00009932226,0.0006603151,0.2345477,0.001247574,0.7497856,0.001426625,0.004129022],"study_design_scores_gemma":[0.000574436,0.0001432623,0.005726359,0.00001382011,0.00003059124,0.00001603862,0.0002135819,0.9665124,0.0011766,0.006861535,0.01839388,0.0003374464],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1004292,0.00001400072,0.8950629,0.003128803,0.00002671195,0.00014997,5.951175e-7,0.0001946867,0.0009931078],"genre_scores_gemma":[0.995721,0.00001224861,0.002660059,0.001351957,0.00004716399,9.295194e-7,0.000001328523,0.000006553869,0.0001987506],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8952918,"threshold_uncertainty_score":0.2820851,"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."}}