{"id":"W2890608676","doi":"10.1609/aaai.v33i01.33011443","title":"Improving Optimization Bounds Using Machine Learning: Decision Diagrams Meet Deep Reinforcement Learning","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Formal Methods in Verification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Bounding overwatch; Reinforcement learning; Computer science; Maximum cut; Mathematical optimization; Set (abstract data type); Relaxation (psychology); Perspective (graphical); Optimization problem; Function (biology); Artificial intelligence; Algorithm; Mathematics; Theoretical computer science; Graph","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":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002206805,0.0005710909,0.0006262591,0.0003835923,0.0005217074,0.001108,0.003700722,0.000435607,0.00005384961],"category_scores_gemma":[0.002825046,0.0004834818,0.0002751228,0.0007892134,0.0002358884,0.0008046995,0.00327854,0.001626571,0.0000332516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003542169,"about_ca_system_score_gemma":0.0002860747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002139407,"about_ca_topic_score_gemma":0.000009056039,"domain_scores_codex":[0.9956093,0.0001129144,0.001331668,0.001167579,0.001199112,0.0005793871],"domain_scores_gemma":[0.9952354,0.0001982527,0.002304153,0.0007635556,0.00137096,0.0001276317],"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":[0.00007442547,0.00005694258,0.0002839909,0.0001697288,0.0000222233,2.488578e-7,0.001101279,0.7868147,0.006152969,0.1491147,0.000002649218,0.05620611],"study_design_scores_gemma":[0.00003604769,0.0002291443,0.0000148086,0.0006535763,0.00003583269,0.0000042179,0.0001987764,0.8735188,0.10511,0.01973524,0.00002922212,0.000434346],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02105412,0.00007590742,0.9737866,0.0001824504,0.001692102,0.0009765002,0.000001275195,0.0002030477,0.002028006],"genre_scores_gemma":[0.7096888,0.000128861,0.2898347,0.00004385391,0.00008830566,0.00003660474,0.000005426242,0.00003667031,0.0001367259],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6886348,"threshold_uncertainty_score":0.999929,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08560422175768673,"score_gpt":0.3233321272910276,"score_spread":0.2377279055333408,"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."}}