{"id":"W2563280975","doi":"10.1609/aaai.v30i1.10320","title":"Delay-Tolerant Online Convex Optimization: Unified Analysis and Adaptive-Gradient Algorithms","year":2016,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Sparse and Compressive Sensing Techniques","field":"Engineering","cited_by":32,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Innovates","keywords":"Online algorithm; Regret; Computer science; Convexity; Reduction (mathematics); Algorithm; Convex optimization; Gradient descent; Convex function; Smoothness; Mathematical optimization; Unification; Regular polygon; Mathematics; Artificial intelligence; Machine learning","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001220635,0.0001928039,0.000285395,0.0001804508,0.00007859895,0.00005509792,0.0003437091,0.00007894154,0.00006479145],"category_scores_gemma":[0.0000530166,0.0001226911,0.00009258848,0.000531964,0.0002271045,0.0001265458,0.00008327597,0.0001249408,0.000005384101],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003223798,"about_ca_system_score_gemma":0.00001489222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003029928,"about_ca_topic_score_gemma":0.00001559435,"domain_scores_codex":[0.9989432,0.000008612583,0.0003553798,0.0002646152,0.0002156394,0.0002125472],"domain_scores_gemma":[0.9991963,0.00005702011,0.0001243015,0.00016516,0.0003873112,0.00006992384],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003479234,0.0003952104,0.001622025,0.00006801789,0.001154184,0.000006236444,0.001795473,0.05508217,0.2418438,0.324673,0.0003395918,0.3726723],"study_design_scores_gemma":[0.00002601339,0.00008855875,0.0002164352,0.0001808142,0.0001091793,0.000003097952,0.0001857458,0.6573731,0.3326569,0.008932079,0.00004413772,0.0001838793],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3610793,0.0001023149,0.633417,0.001069038,0.0002554585,0.000388581,0.00003807722,0.0004019896,0.003248275],"genre_scores_gemma":[0.9913201,0.0002666698,0.008237827,0.00004498114,0.00004300061,0.000008838832,0.000001448108,0.00001646367,0.00006071212],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6302407,"threshold_uncertainty_score":0.5003198,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05935458360672487,"score_gpt":0.2635845540217784,"score_spread":0.2042299704150535,"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."}}