{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003197062,0.0003332006,0.000315371,0.0002993988,0.0002083459,0.0002789667,0.001457443,0.00021983,0.00005325859],"category_scores_gemma":[0.00003961538,0.0003217402,0.0001524977,0.0006129781,0.0002777081,0.0003008581,0.001113291,0.0006224481,0.0002361929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064361,"about_ca_system_score_gemma":0.0001674255,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000346876,"about_ca_topic_score_gemma":0.0000499446,"domain_scores_codex":[0.9978303,0.0002712496,0.0002175589,0.001079791,0.0002061224,0.0003949919],"domain_scores_gemma":[0.9983621,0.0001820123,0.0002483267,0.0009164225,0.0001306217,0.0001605402],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000642766,0.0000420596,0.0006598652,0.00003269348,0.00007666827,0.0002959678,0.0008581805,0.1378348,0.00003298407,0.8595516,0.00002155016,0.0005293269],"study_design_scores_gemma":[0.0007157843,0.0000947634,0.006660068,0.000141864,0.00004409151,0.000005475429,0.0003119172,0.6853488,0.00002891688,0.305844,0.0003373364,0.0004669751],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1996787,0.000008992866,0.797275,0.0002453558,0.0003347514,0.0002402626,0.000004933183,0.0005717714,0.001640225],"genre_scores_gemma":[0.9826968,0.00005839199,0.015737,0.0000890668,0.00005637901,0.000002128822,0.00003071172,0.00003429143,0.001295246],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7830181,"threshold_uncertainty_score":0.9999235,"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."}}