{"id":"W4380993971","doi":"10.48550/arxiv.2306.08838","title":"Differentially Private Domain Adaptation with Theoretical Guarantees","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Leverage (statistics); Domain adaptation; Computer science; Domain (mathematical analysis); Adaptation (eye); Lipschitz continuity; Convex optimization; Regular polygon; Sample (material); Mathematical optimization; Optimization problem; Artificial intelligence; Machine learning; Algorithm; Mathematics; Classifier (UML)","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":[0.007055258,0.001385521,0.002097429,0.0008125513,0.00129969,0.002489538,0.00343674,0.002896142,0.00340468],"category_scores_gemma":[0.03509052,0.0008143228,0.001222586,0.001552975,0.002860337,0.007065585,0.007422254,0.005856542,0.001941149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002241865,"about_ca_system_score_gemma":0.002604294,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009518099,"about_ca_topic_score_gemma":0.001001118,"domain_scores_codex":[0.995015,0.002024268,0.0001956469,0.001219187,0.001191868,0.0003541494],"domain_scores_gemma":[0.9748465,0.01450408,0.001112066,0.007899185,0.001132031,0.0005061415],"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":[0.001073304,0.0005120469,0.002530295,0.0003361372,0.0001582745,0.0002440798,0.0004401434,0.544107,0.008764436,0.2303057,0.01110247,0.2004262],"study_design_scores_gemma":[0.00005387228,0.00005804708,0.0002510866,0.00001619129,0.00001468905,0.000122014,0.00003600927,0.8393017,0.003215562,0.1552645,0.001645915,0.00002039401],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01247054,0.0003013941,0.9832711,0.0008424835,0.0000448746,0.00008760217,0.0001441701,0.0008448663,0.00199303],"genre_scores_gemma":[0.6705268,0.0007635683,0.3178407,0.001054277,0.0003141633,0.0005956742,0.0008205594,0.0004056803,0.007678571],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007055258,"threshold_uncertainty_score":0.03731221,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0669261931874121,"score_gpt":0.1871211815737866,"score_spread":0.1201949883863745,"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."}}