{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:53:28Z","timestamp":1782762808737,"version":"3.54.5"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"European Research Council (ERC) through European Union\u2019s Horizon Europe Program","award":["101198347"],"award-info":[{"award-number":["101198347"]}]},{"name":"Open Fellowship of EPSRC","award":["EP\/W024101\/1"],"award-info":[{"award-number":["EP\/W024101\/1"]}]},{"name":"Engineering and Physical Sciences Research Council (EPSRC) Project","award":["EP\/X011852\/1"],"award-info":[{"award-number":["EP\/X011852\/1"]}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["101163414"],"award-info":[{"award-number":["101163414"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Areas Inf. Theory"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/jsait.2026.3705302","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T20:13:30Z","timestamp":1781813610000},"page":"290-301","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty Quantification and Data Efficiency in AI: An Information-Theoretic Perspective"],"prefix":"10.1109","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9898-3209","authenticated-orcid":false,"given":"Osvaldo","family":"Simeone","sequence":"first","affiliation":[{"name":"Institute for Intelligent Networked Systems, Northeastern University London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8951-8583","authenticated-orcid":false,"given":"Yaniv","family":"Romano","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering and the Department of Computer Science, Technion—Israel Institute of Technology, Haifa, Israel"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802498"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2024.3447472"},{"key":"ref3","article-title":"How to bridge the sim-to-real gap in digital twin-aided telecommunication networks","author":"Ruah","year":"2025","journal-title":"arXiv:2507.07067"},{"key":"ref4","article-title":"Data efficient deep learning for medical image analysis: A survey","author":"Kumari","year":"2023","journal-title":"arXiv:2310.06557"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-05946-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/9781009072205"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1017\/9781009579551"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1561\/2200000112"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1002\/qute.202300311"},{"issue":"132","key":"ref11","first-page":"1","article-title":"An optimization-centric view on Bayes\u2019 rule: Reviewing and generalizing variational inference","volume":"23","author":"Knoblauch","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/b106715"},{"key":"ref13","article-title":"Theoretical foundations of conformal prediction","author":"Angelopoulos","year":"2024","journal-title":"arXiv:2411.11824"},{"key":"ref14","article-title":"Comprehensive exploration of synthetic data generation: A survey","author":"Bauer","year":"2024","journal-title":"arXiv:2401.02524"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2024.07.005"},{"key":"ref16","article-title":"Adaptive prediction-powered AutoEval with reliability and efficiency guarantees","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Park"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1126\/science.adi6000"},{"key":"ref18","first-page":"41413","article-title":"Doubly-robust self-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 36","author":"Ding"},{"key":"ref19","article-title":"Synthetic-powered predictive inference","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Bashari"},{"key":"ref20","article-title":"General synthetic-powered inference","author":"Bashari","year":"2025","journal-title":"arXiv:2509.20345"},{"key":"ref21","volume-title":"Machine Learning: A Bayesian and Optimization Perspective","author":"Theodoridis","year":"2015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1561\/2200000052"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3295168"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"issue":"168","key":"ref25","first-page":"1","article-title":"Asymptotic normality, concentration, and coverage of generalized posteriors","volume":"22","author":"Miller","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref26","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Welling"},{"key":"ref27","article-title":"Bayesian active learning for classification and preference learning","author":"Houlsby","year":"2011","journal-title":"arXiv:1112.5745"},{"key":"ref28","article-title":"Predictive uncertainty estimation via prior networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Malinin"},{"key":"ref29","first-page":"1184","article-title":"Decomposition of uncertainty in Bayesian deep learning for efficient and risk-sensitive learning","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Depeweg"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2022.3169440"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2024.3365728"},{"key":"ref32","article-title":"Empirical risk minimization with $f$\n-divergence regularization","author":"Daunas","year":"2026","journal-title":"arXiv:2601.13191"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkad005"},{"key":"ref35","first-page":"83430","article-title":"TuneTables: Context optimization for scalable prior-data fitted networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 37","author":"Cherepanova"},{"key":"ref36","article-title":"Transformers can do Bayesian inference","author":"M\u00fcller","year":"2021","journal-title":"arXiv:2112.10510"},{"key":"ref37","first-page":"25444","article-title":"PFNs4BO: In-context learning for Bayesian optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"M\u00fcller"},{"key":"ref38","article-title":"TabPFN: A transformer that solves small tabular classification problems in a second","author":"Hollmann","year":"2022","journal-title":"arXiv:2207.01848"},{"key":"ref39","article-title":"CausalPFN: Amortized causal effect estimation via in-context learning","author":"Balazadeh","year":"2025","journal-title":"arXiv:2506.07918"},{"key":"ref40","first-page":"2524","article-title":"Information-theoretic analysis of generalization capability of learning algorithms","volume-title":"Proc. Adv. neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Xu"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2023.3329617"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1214\/lnms\/1199996415"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1561\/2200000100"},{"key":"ref44","article-title":"Computing nonvacuous generalization bounds for deep (Stochastic) neural networks with many more parameters than training data","author":"Dziugaite","year":"2017","journal-title":"arXiv:1703.11008"},{"key":"ref45","article-title":"Non-vacuous generalization bounds for large language models","author":"Lotfi","year":"2023","journal-title":"arXiv:2312.17173"},{"key":"ref46","article-title":"Deep learning is not so mysterious or different","author":"Gordon Wilson","year":"2025","journal-title":"arXiv:2503.02113"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3292071"},{"key":"ref48","article-title":"Decision theoretic foundations for conformal prediction: Optimal uncertainty quantification for risk-averse agents","author":"Kiyani","year":"2025","journal-title":"arXiv:2502.02561"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2024.3368229"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3203"},{"key":"ref51","volume-title":"Inequalities: Theory of Majorization and Its Applications","author":"Marshall","year":"2010"},{"key":"ref52","first-page":"79540","article-title":"Credal deep ensembles for uncertainty quantification","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 37","author":"Cuzzolin"},{"key":"ref53","first-page":"1321","article-title":"On calibration of modern neural networks","volume-title":"Proc. 34th Intl. Conf. Mach. Learn.","author":"Guo"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2025.3629292"},{"key":"ref55","first-page":"85932","article-title":"Large language models must be taught to know what they don\u2019t know","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 37","author":"Bhatt"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaaa017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-013-5355-6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkaf008"},{"key":"ref59","article-title":"Conformal prediction with local weights: Randomization enables local guarantees","author":"Hore","year":"2023","journal-title":"arXiv:2310.07850"},{"key":"ref60","first-page":"3581","article-title":"Classification with valid and adaptive coverage","volume-title":"Proc. Adv. neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Romano"},{"key":"ref61","article-title":"Conformalized quantile regression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Romano"},{"key":"ref62","article-title":"A unified comparative study with generalized conformity scores for multi-output conformal regression","author":"Dheur","year":"2025","journal-title":"arXiv:2501.10533"},{"key":"ref63","article-title":"Multivariate conformal prediction using optimal transport","author":"Klein","year":"2025","journal-title":"arXiv:2502.03609"},{"key":"ref64","first-page":"2526","article-title":"Conformal prediction under covariate shift","volume-title":"Proc. Adv. neural Inf. Process. Syst. (NeurIPS)","volume":"32","author":"Tibshirani"},{"key":"ref65","article-title":"Conformal risk control","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Angelopoulos"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/1012"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3478535"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1214\/24-AOAS1998"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63237.2025.11226701"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT57864.2024.10619313"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT63088.2025.11195484"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-01681-4"},{"key":"ref73","article-title":"Weak-to-strong generalization: Eliciting strong capabilities with weak supervision","author":"Burns","year":"2023","journal-title":"arXiv:2312.09390"},{"key":"ref74","article-title":"PPI++: Efficient prediction-powered inference","author":"Angelopoulos","year":"2023","journal-title":"arXiv:2311.01453"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2322083121"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2024.3503543"},{"key":"ref77","article-title":"Prediction-powered semi-supervised learning with online power tuning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Shoham"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1214\/14-sts500"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1214\/16-STS589"},{"key":"ref80","article-title":"Strong model collapse","author":"Dohmatob","year":"2024","journal-title":"arXiv:2410.04840"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3594263"},{"key":"ref82","article-title":"PAC prediction sets under covariate shift","author":"Park","year":"2021","journal-title":"arXiv:2106.09848"},{"key":"ref83","article-title":"Prismatic synthesis: Gradient-based data diversification boosts generalization in LLM reasoning","author":"Jung","year":"2025","journal-title":"arXiv:2505.20161"}],"container-title":["IEEE Journal on Selected Areas in Information Theory"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8700143\/11395188\/11570920.pdf?arnumber=11570920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T19:42:35Z","timestamp":1782762155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11570920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/jsait.2026.3705302","relation":{},"ISSN":["2641-8770"],"issn-type":[{"value":"2641-8770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}