{"id":"W3111605110","doi":"10.1609/aaai.v35i8.16859","title":"Provable Benefits of Overparameterization in Model Compression: From Double Descent to Pruning Neural Networks","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"National Science Foundation","keywords":"Pruning; Computer science; Artificial neural network; Feature (linguistics); Deep neural networks; Parameterized complexity; Artificial intelligence; Machine learning; Algorithm","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":[0.00008523618,0.0001522599,0.0002457331,0.00007565448,0.00004062117,0.0000612366,0.000351733,0.00008121289,0.00001660899],"category_scores_gemma":[0.00005346498,0.00013463,0.000050586,0.0004170318,0.00004526587,0.00013539,0.0001568653,0.0001999617,0.000001590773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003295919,"about_ca_system_score_gemma":0.00002257922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006534321,"about_ca_topic_score_gemma":0.00002764639,"domain_scores_codex":[0.9989339,0.000006853919,0.0004085323,0.0002354812,0.0002105215,0.0002047211],"domain_scores_gemma":[0.999302,0.00003055336,0.0001135801,0.0001725302,0.0003361596,0.00004517789],"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":[0.00007826859,0.00006511962,0.0002792103,0.00001728628,0.000007356934,2.94319e-7,0.0004064252,0.7387419,0.2338206,0.01539575,0.00004096385,0.01114685],"study_design_scores_gemma":[0.00001577718,0.00002176144,0.0001082076,0.0003887169,0.000004549065,3.633468e-7,0.00006661248,0.5101828,0.4853706,0.003767795,0.00000200502,0.00007085311],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9660268,0.00007796525,0.03167985,0.0001392218,0.0001750152,0.0002904682,0.000005432125,0.00009089064,0.001514327],"genre_scores_gemma":[0.9956431,0.0000491736,0.004175196,0.00005148377,0.00002866609,0.00001606983,0.000002240298,0.00001796363,0.00001608658],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.25155,"threshold_uncertainty_score":0.5490051,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0892116449821859,"score_gpt":0.275641139043692,"score_spread":0.1864294940615061,"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."}}