{"id":"W2963812988","doi":"10.1016/j.tcs.2013.09.024","title":"Adaptive and optimal online linear regression on <mml:math xmlns:mml=\"http://www.w3.org/1998/Math/MathML\" altimg=\"si1.gif\" overflow=\"scroll\"><mml:msup><mml:mrow><mml:mi>ℓ</mml:mi></mml:mrow><mml:mrow><mml:mn>1</mml:mn></mml:mrow></mml:msup></mml:math>-balls","year":2013,"lang":"lv","type":"article","venue":"Theoretical Computer Science","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Agence Nationale de la Recherche; European Commission","keywords":"Regret; Ball (mathematics); Dimension (graph theory); Mathematics; Linear regression; Minimax; Algorithm; Discrete mathematics; Applied mathematics; Computer science; Combinatorics; Mathematical optimization; Statistics; Mathematical analysis","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":[0.004282832,0.001948511,0.002558528,0.001182106,0.0008037539,0.002557537,0.002196364,0.001789942,0.02342508],"category_scores_gemma":[0.03116689,0.0009913287,0.001432762,0.001926162,0.001694988,0.00382569,0.003336702,0.004585477,0.008130963],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002312764,"about_ca_system_score_gemma":0.003376775,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00840398,"about_ca_topic_score_gemma":0.01402451,"domain_scores_codex":[0.9964448,0.001653284,0.0001900465,0.0006098285,0.0007405353,0.0003615496],"domain_scores_gemma":[0.9817837,0.01355033,0.0006372107,0.00197645,0.001557685,0.0004947513],"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":[0.0007997151,0.0003733263,0.00150578,0.000524695,0.0001621334,0.0002636639,0.0001842651,0.3816894,0.001799452,0.325168,0.08989715,0.1976324],"study_design_scores_gemma":[0.00006405408,0.00005595769,0.0004950797,0.00005990134,0.00002531715,0.00004737546,0.00002738476,0.8523829,0.0007496527,0.139566,0.006506323,0.00001997261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01228682,0.00148508,0.9597219,0.003374275,0.0004053002,0.0001061255,0.001212472,0.002070654,0.01933735],"genre_scores_gemma":[0.4166526,0.002964139,0.4654971,0.001733008,0.001386788,0.0008186913,0.006519074,0.001811128,0.1026174],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02342508,"threshold_uncertainty_score":0.07836467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03032311422587168,"score_gpt":0.2978322730377435,"score_spread":0.2675091588118718,"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."}}