{"id":"W4385288900","doi":"10.1145/3592144","title":"∇-Prox: Differentiable Proximal Algorithm Modeling for Large-Scale Optimization","year":2023,"lang":"en","type":"article","venue":"ACM Transactions on Graphics","topic":"Advanced Neural Network Applications","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"National Natural Science Foundation of China; Bundesministerium für Wirtschaft und Klimaschutz","keywords":"Computer science; Optimization problem; Differentiable function; Deep learning; Artificial intelligence; Mathematical optimization; Artificial neural network; Algorithm; 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":[0.0001492372,0.0001675848,0.0001437626,0.0002861349,0.0006789023,0.00008780979,0.0007535428,0.00009838777,0.000007095291],"category_scores_gemma":[0.00001248817,0.0001731343,0.0001341681,0.001812448,0.00002216899,0.0004490982,0.00002486148,0.0002130316,0.00001877309],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002429172,"about_ca_system_score_gemma":0.00002816469,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002202019,"about_ca_topic_score_gemma":0.00001033666,"domain_scores_codex":[0.998574,0.00002468521,0.000239914,0.0005065174,0.0002329548,0.0004219836],"domain_scores_gemma":[0.9986636,0.0001604525,0.00005539634,0.0008896376,0.0001369361,0.00009398057],"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":[0.000005941426,0.000123506,0.000004178649,0.00001170057,0.00001666913,4.750927e-7,0.0001161643,0.9738116,0.00005799704,0.005908601,0.0001321271,0.01981105],"study_design_scores_gemma":[0.0003689358,0.00006226166,0.000009028414,0.00001193045,0.00001685043,0.000002332536,0.00002817734,0.9663702,0.000501851,0.03175212,0.0006967454,0.0001795847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004731225,0.00001649102,0.9959064,0.001764908,0.0002128699,0.0006690348,0.00005759904,0.000878944,0.0000205972],"genre_scores_gemma":[0.06470654,0.0002368506,0.9332876,0.0003198584,0.00006199975,0.0009650636,0.00007444041,0.00004127161,0.0003064201],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06423342,"threshold_uncertainty_score":0.7060211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03029827848921085,"score_gpt":0.2765455629866552,"score_spread":0.2462472844974443,"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."}}