{"id":"W4385749309","doi":"10.1287/trsc.2021.0110","title":"Iterative Backpropagation Method for Efficient Gradient Estimation in Bilevel Network Equilibrium Optimization Problems","year":2023,"lang":"en","type":"article","venue":"Transportation Science","topic":"Transportation Planning and Optimization","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Bilevel optimization; Mathematical optimization; Computer science; Backpropagation; Optimization problem; Iterative method; Iterative and incremental development; Matching (statistics); Mathematics; Artificial neural network; Artificial intelligence; Statistics","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":[0.001210447,0.001530615,0.001198615,0.0007143285,0.0004980162,0.0008392292,0.001174494,0.001270794,0.002032807],"category_scores_gemma":[0.003936523,0.0006571286,0.0007542882,0.0008436591,0.000727148,0.001153012,0.00103141,0.002195574,0.0004594333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009285259,"about_ca_system_score_gemma":0.002098474,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01352829,"about_ca_topic_score_gemma":0.01153845,"domain_scores_codex":[0.9995759,0.0001408126,0.0000346239,0.00006535833,0.0001255769,0.00005766966],"domain_scores_gemma":[0.9988754,0.0007050915,0.00007337362,0.00004749631,0.0002728202,0.00002576548],"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":[0.00003596249,0.00003701976,0.0004634769,0.0000929872,0.00004913436,0.00006563622,0.00006873842,0.9099253,0.001620697,0.00846309,0.001502033,0.07767593],"study_design_scores_gemma":[0.00000435802,0.000005959554,0.00002762674,0.000003725121,0.000002469652,0.000004944848,0.000003619298,0.9980087,0.0002375369,0.001429584,0.0002694597,0.000002019132],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004771441,0.0002156844,0.9934016,0.0001530336,0.00002899229,0.00002690047,0.00002429875,0.0003970166,0.0009811288],"genre_scores_gemma":[0.2868653,0.0006011696,0.7073334,0.0002744133,0.00007985151,0.0004220332,0.0002595942,0.0002704051,0.003893895],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01352829,"threshold_uncertainty_score":0.0268991,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04052427478692713,"score_gpt":0.3498774530552591,"score_spread":0.309353178268332,"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."}}