{"id":"W2551153860","doi":"10.1287/moor.2016.0817","title":"A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications","year":2016,"lang":"en","type":"article","venue":"Mathematics of Operations Research","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":342,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia, Okanagan Campus; University of British Columbia","funders":"","keywords":"Lipschitz continuity; Mathematics; Sublinear function; Convexity; Gradient descent; Subgradient method; Lemma (botany); Uniqueness; Applied mathematics; Pointwise; Rate of convergence; Bregman divergence; Convex function; Mathematical optimization; Measure (data warehouse); Regular polygon; Mathematical analysis; Key (lock); Computer science; Geometry","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":[0.0007717144,0.0001021061,0.0001963199,0.0002228025,0.0001701878,0.00006941197,0.0001755727,0.00005896358,0.00004163542],"category_scores_gemma":[0.0002443059,0.00007442963,0.00003044126,0.0003534677,0.0001474589,0.00008647882,0.0001095899,0.0001275989,0.00001479679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004073866,"about_ca_system_score_gemma":0.00002050142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001207212,"about_ca_topic_score_gemma":0.00003460054,"domain_scores_codex":[0.9990362,0.0000805397,0.0002886166,0.0001549094,0.0002283764,0.000211354],"domain_scores_gemma":[0.9986481,0.0003612457,0.00001597407,0.0004587609,0.0004435813,0.00007232185],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000105881,0.0004682164,0.0002187274,0.000661899,0.0002322212,0.000004812386,0.002779719,0.001507942,0.5435165,0.3239858,0.007662383,0.1189513],"study_design_scores_gemma":[0.00130735,0.0002978643,0.0008015786,0.00180941,0.0001036861,0.00007428722,0.0007235745,0.3508985,0.4913865,0.06364337,0.08803673,0.0009171325],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05379301,0.0007621305,0.9382672,0.0004904674,0.00002216967,0.001062386,0.00002495163,0.0002284266,0.005349273],"genre_scores_gemma":[0.5878187,0.0006140092,0.4108951,0.000008681486,0.00004231521,0.0002485413,0.000004294684,0.00003191053,0.0003363495],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5340257,"threshold_uncertainty_score":0.3035152,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06474276344782105,"score_gpt":0.3797376502487932,"score_spread":0.3149948868009722,"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."}}