{"id":"W4378499052","doi":"10.48550/arxiv.2305.15653","title":"Alternating Subgradient Methods for Convex-Concave Saddle-Point Problems","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Subgradient method; Mathematics; Iterated function; Sequence (biology); Saddle point; Convex function; Mathematical optimization; Regular polygon; Convex optimization; Saddle; Bounded function; Linear matrix inequality; Rate of convergence; Applied mathematics; Mathematical analysis; Computer science; Geometry","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.007588802,0.0005560964,0.00102792,0.001207107,0.0004424432,0.0004260954,0.003495926,0.0004535865,0.0001736636],"category_scores_gemma":[0.005856866,0.0005334239,0.0007283771,0.001653483,0.0004253293,0.0004430547,0.003716735,0.001176599,0.0005363313],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006708761,"about_ca_system_score_gemma":0.0003947931,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002347514,"about_ca_topic_score_gemma":0.0001427655,"domain_scores_codex":[0.9936978,0.0008779826,0.0009307211,0.002790502,0.0006461469,0.001056808],"domain_scores_gemma":[0.9879941,0.007078127,0.000942056,0.002082151,0.001446447,0.0004570701],"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":[0.0002033428,0.000151259,0.002298479,0.0002155496,0.0003811253,0.0003466102,0.001323931,0.938337,0.0002179214,0.01737032,0.002092385,0.03706213],"study_design_scores_gemma":[0.0007762457,0.0001117362,0.0003508931,0.00009888705,0.00004951801,0.00000366385,0.0006799025,0.5775557,0.0006624492,0.4126574,0.006562486,0.0004912043],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02815596,0.0001538879,0.9659954,0.0002879233,0.002160345,0.001873945,0.0001872785,0.0003120454,0.0008732728],"genre_scores_gemma":[0.9005832,0.0003048349,0.06099832,0.00009483217,0.0004726817,0.00005207813,0.0000918025,0.0001629555,0.03723927],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9049971,"threshold_uncertainty_score":0.9997118,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5393300625195931,"score_gpt":0.4107714676144865,"score_spread":0.1285585949051066,"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."}}