{"id":"W4285600461","doi":"10.24963/ijcai.2022/548","title":"Private Stochastic Convex Optimization and Sparse Learning with Heavy-tailed Data Revisited","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Stochastic Gradient Optimization Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology","keywords":"Bounded function; Lipschitz continuity; Convex optimization; Mathematics; Mathematical optimization; Regular polygon; Constraint (computer-aided design); Moment (physics); Upper and lower bounds; Curse of dimensionality; Estimator; Monotonic function; Optimization problem; Convex function; Applied mathematics; Mathematical analysis; Statistics; Physics","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":[0.006936723,0.001577071,0.002740242,0.0008831569,0.0007694722,0.002148817,0.002710128,0.002641311,0.001962944],"category_scores_gemma":[0.02866687,0.001083664,0.001033806,0.001921501,0.004398534,0.005711586,0.003817994,0.005415292,0.0003854985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002459266,"about_ca_system_score_gemma":0.002083767,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002522188,"about_ca_topic_score_gemma":0.00173406,"domain_scores_codex":[0.995182,0.002286423,0.000188839,0.0007822166,0.001118777,0.0004417362],"domain_scores_gemma":[0.9771738,0.01763533,0.001436473,0.002120473,0.001134385,0.0004996317],"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":[0.0002117146,0.0001117019,0.001406109,0.0003311583,0.0001150127,0.0003277495,0.0001422761,0.6821488,0.00179033,0.2812147,0.003388476,0.02881208],"study_design_scores_gemma":[0.00002222931,0.00003758808,0.0001667815,0.00002046035,0.00000842492,0.00006224152,0.00001682685,0.9091899,0.000468637,0.08944354,0.0005503721,0.00001290662],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01437737,0.0007823136,0.9811659,0.001657657,0.00005952019,0.00004566013,0.0001461729,0.0001186208,0.001646749],"genre_scores_gemma":[0.7960533,0.00262082,0.1932861,0.001308524,0.0007814333,0.0003084101,0.0005618141,0.000219755,0.004859741],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.006936723,"threshold_uncertainty_score":0.03668535,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07149497516497867,"score_gpt":0.2739307753526263,"score_spread":0.2024358001876476,"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."}}