{"id":"W4394838699","doi":"10.48550/arxiv.2404.08073","title":"Spurious Stationarity and Hardness Results for Bregman Proximal-Type Algorithms","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Spurious relationship; Bregman divergence; Stationary point; Euclidean geometry; Divergence (linguistics); Coordinate descent; Regular polygon; Point (geometry); Mathematics; Descent (aeronautics); Mathematical optimization; Metric (unit); Algorithm; Type (biology); Computer science; Applied mathematics; Mathematical analysis; Statistics; Physics; 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":[0.0001114578,0.0002758933,0.0002679721,0.0001832625,0.00007593905,0.00008901939,0.0002310769,0.0002677935,0.000003017392],"category_scores_gemma":[0.00002557799,0.0003279693,0.00009359105,0.0001850816,0.00007141549,0.00006806554,0.0004215161,0.0004410634,0.00001135989],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001117687,"about_ca_system_score_gemma":0.00005893858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006591734,"about_ca_topic_score_gemma":0.00002713497,"domain_scores_codex":[0.9989171,0.00002311064,0.0001667929,0.0006082365,0.00005128983,0.0002334538],"domain_scores_gemma":[0.9992141,0.00005985882,0.00005586334,0.0004253006,0.0001589547,0.00008598511],"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":[0.001144336,0.0002647241,0.0007170071,0.003992862,0.001989398,0.001993118,0.002239428,0.7568282,0.001828985,0.09176191,0.1213979,0.01584207],"study_design_scores_gemma":[0.0004923514,0.00007286528,0.0003259843,0.0003423515,0.0001998,0.000009599585,0.0000597357,0.8582759,0.001810722,0.1315542,0.00629187,0.000564657],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8397763,0.001471449,0.1426915,0.0001692435,0.003047127,0.001791749,0.0007730439,0.003874812,0.006404736],"genre_scores_gemma":[0.9949348,0.0004104583,0.003138892,0.00001807991,0.000129602,0.000002750208,0.0001194932,0.00005300052,0.001192899],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1551585,"threshold_uncertainty_score":0.9999172,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0746037854122669,"score_gpt":0.2053920090670331,"score_spread":0.1307882236547662,"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."}}