{"id":"W4376607417","doi":"10.1137/1.9781611977714.16","title":"Exponential Convergence of Sinkhorn Under Regularization Scheduling","year":2023,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Optimization and Search Problems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Logarithm; Scaling; Regularization (linguistics); Mathematical optimization; Exponential function; Rate of convergence; Computer science; Applied mathematics; Convergence (economics); Mathematics; Key (lock); Artificial intelligence","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":[0.001739061,0.0009577209,0.0008928614,0.0006509924,0.0005832693,0.0008312457,0.001100741,0.001276686,0.003110484],"category_scores_gemma":[0.00853894,0.0003739314,0.0007593185,0.0005187507,0.001580068,0.001875934,0.001693576,0.002025012,0.0007993002],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009529518,"about_ca_system_score_gemma":0.0009320759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002067782,"about_ca_topic_score_gemma":0.00239564,"domain_scores_codex":[0.9993306,0.0002321869,0.00003091934,0.0001236191,0.0002073488,0.00007514592],"domain_scores_gemma":[0.9975714,0.001475949,0.0001383164,0.0003442597,0.0003706273,0.00009943495],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002953976,0.0001013383,0.001216837,0.0002370919,0.00007619595,0.0001345051,0.0002105014,0.569864,0.01320989,0.3213709,0.008674004,0.08460928],"study_design_scores_gemma":[0.000007897287,0.00001882048,0.00004792572,0.000009347749,0.000003123642,0.00001347789,0.000008616775,0.9710919,0.001155977,0.02657228,0.001065227,0.000005424507],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01760383,0.0003179897,0.9744717,0.0003704565,0.0001083043,0.00004679611,0.00004465533,0.0004137984,0.006622537],"genre_scores_gemma":[0.3291368,0.0004851256,0.6541029,0.0005968526,0.0001245355,0.000290226,0.0002895724,0.0006214269,0.0143525],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003110484,"threshold_uncertainty_score":0.01040566,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09839758548177648,"score_gpt":0.2599201215185701,"score_spread":0.1615225360367937,"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."}}