{"id":"W4403580911","doi":"10.48550/arxiv.2410.13577","title":"Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generalization; Sample (material); Compression (physics); Artificial intelligence; Computer science; Mathematics; Physics; 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":[0.009619718,0.00209473,0.002200516,0.001682252,0.001048941,0.002954618,0.003733701,0.003332875,0.003893716],"category_scores_gemma":[0.04513432,0.001341959,0.001581142,0.00174057,0.004332317,0.009752383,0.005129911,0.009628977,0.0007685119],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003907281,"about_ca_system_score_gemma":0.00224819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002943477,"about_ca_topic_score_gemma":0.003567487,"domain_scores_codex":[0.9965649,0.001565579,0.0001457663,0.0006038539,0.0008734718,0.0002464574],"domain_scores_gemma":[0.9774584,0.01745254,0.001013274,0.002485073,0.001110625,0.0004802102],"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":[0.0001682865,0.00007997713,0.000813004,0.0001630354,0.00009865427,0.0001170018,0.000204332,0.579123,0.0008241878,0.374964,0.002808926,0.04063557],"study_design_scores_gemma":[0.000009516117,0.00002330341,0.00007022479,0.00003312569,0.0000113506,0.00002419209,0.00001094017,0.7945433,0.000413179,0.2044517,0.0003980855,0.00001121156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01217801,0.0008587457,0.9820067,0.001333905,0.00004783431,0.00004525455,0.0001527597,0.0003400753,0.003036622],"genre_scores_gemma":[0.6654192,0.002612258,0.3191844,0.001883632,0.0005974109,0.0007241576,0.0008724181,0.0007736739,0.007932885],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.009619718,"threshold_uncertainty_score":0.05087453,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1479020429098674,"score_gpt":0.2465707154410324,"score_spread":0.09866867253116499,"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."}}