{"id":"W4415112137","doi":"10.48550/arxiv.2506.12648","title":"Glocal Smoothness: Line search and adaptive step sizes can help in theory too!","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Lipschitz continuity; Smoothness; Line search; Iterated function; Constant (computer programming); Conjugate gradient method; Gradient descent; Line (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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00413241,0.002030744,0.001263836,0.0009085156,0.0008789288,0.00328575,0.002247247,0.003226776,0.01339091],"category_scores_gemma":[0.03512023,0.000981172,0.001520092,0.001248288,0.003984977,0.008458159,0.002959274,0.008941351,0.003666728],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00136127,"about_ca_system_score_gemma":0.001793521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002709682,"about_ca_topic_score_gemma":0.00225975,"domain_scores_codex":[0.9972513,0.001339185,0.0001204138,0.0004800587,0.0006634729,0.0001455371],"domain_scores_gemma":[0.9842032,0.01061151,0.0008807897,0.002989041,0.001006371,0.0003090641],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0002209074,0.000114253,0.001089078,0.0004097226,0.00008831404,0.0001373378,0.0002122068,0.106738,0.002467276,0.769014,0.01484885,0.1046601],"study_design_scores_gemma":[0.00008263258,0.0001380169,0.0005353594,0.0001825698,0.00003962967,0.0001452185,0.0000529182,0.4150363,0.002948307,0.5534078,0.02736909,0.00006217782],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002723392,0.001215555,0.9834019,0.002998494,0.0002785825,0.00004982468,0.00007328511,0.0006236175,0.00863539],"genre_scores_gemma":[0.1962355,0.00287494,0.7774035,0.003305263,0.000707326,0.0005354183,0.0002474815,0.001764118,0.01692653],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01339091,"threshold_uncertainty_score":0.04479712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07470622997993834,"score_gpt":0.3311479336693621,"score_spread":0.2564417036894238,"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."}}