{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:31:51Z","timestamp":1740123111072,"version":"3.37.3"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T00:00:00Z","timestamp":1696982400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-18-CE23-0015"],"award-info":[{"award-number":["ANR-18-CE23-0015"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council","doi-asserted-by":"crossref","award":["RGPIN-2020-07223"],"award-info":[{"award-number":["RGPIN-2020-07223"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s10994-023-06391-0","type":"journal-article","created":{"date-parts":[[2023,10,11]],"date-time":"2023-10-11T20:13:41Z","timestamp":1697055221000},"page":"519-604","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A general framework for the practical disintegration of PAC-Bayesian bounds"],"prefix":"10.1007","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4836-0809","authenticated-orcid":false,"given":"Paul","family":"Viallard","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pascal","family":"Germain","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amaury","family":"Habrard","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emilie","family":"Morvant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,10,11]]},"reference":[{"key":"6391_CR1","unstructured":"Alquier, P. (2021). User-friendly introduction to PAC-Bayes bounds. CoRR, abs\/2110.11216."},{"key":"6391_CR2","doi-asserted-by":"crossref","unstructured":"Ambroladze, A., Parrado-Hern\u00e1ndez, E., & Shawe-Taylor, J. (2006). Tighter PAC-Bayes bounds. Advances in neural information processing systems (NIPS) (pp. 9\u201316). MIT Press.","DOI":"10.7551\/mitpress\/7503.003.0007"},{"key":"6391_CR3","unstructured":"B\u00e9gin, L., Germain, P., Laviolette, F., & Roy, J. (2014). PAC-Bayesian theory for transductive learning. In: International conference on artificial intelligence and statistics (AISTATS) (Vol. 33, pp. 105\u2013113). JMLR.org."},{"key":"6391_CR4","unstructured":"B\u00e9gin, L., Germain, P., Laviolette, F., & Roy, J. (2016). PAC-Bayesian bounds based on the R\u00e9nyi divergence. In: International conference on artificial intelligence and statistics (AISTATS) (Vol. 51, pp. 435\u2013444). JMLR.org."},{"issue":"10","key":"6391_CR5","doi-asserted-by":"publisher","first-page":"1280","DOI":"10.3390\/e23101280","volume":"23","author":"F Biggs","year":"2021","unstructured":"Biggs, F., & Guedj, B. (2021). Differentiable PAC-Bayes objectives with partially aggregated neural networks. Entropy, 23(10), 1280.","journal-title":"Entropy"},{"key":"6391_CR6","unstructured":"Biggs, F., & Guedj, B. (2022). On margins and derandomisation in PACBayes. International conference on artificial intelligence and statistics (AISTATS) (Vol. 151, pp. 3709\u20133731). PMLR."},{"key":"6391_CR7","doi-asserted-by":"crossref","unstructured":"Blanchard, G., & Fleuret, F. (2007). Occam\u2019s hammer.In:  Annual conference on learning theory (COLT) (Vol. 4539, pp. 112\u2013126). Springer.","DOI":"10.1007\/978-3-540-72927-3_10"},{"key":"6391_CR8","first-page":"499","volume":"2","author":"O Bousquet","year":"2002","unstructured":"Bousquet, O., & Elisseeff, A. (2002). Stability and generalization. Journal of Machine Learning Research, 2, 499\u2013526.","journal-title":"Journal of Machine Learning Research"},{"key":"6391_CR9","unstructured":"Catoni, O. (2007). PAC-Bayesian supervised classification: The thermodynamics of statistical learning. CoRR, abs\/0712.0248."},{"key":"6391_CR10","unstructured":"Dziugaite, G.K., & Roy, D. (2017). Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data. In: Conference on uncertainty in artificial intelligence (UAI). AUAI Press."},{"key":"6391_CR11","unstructured":"Dziugaite, G.K., & Roy, D. (2018). Data-dependent PAC-Bayes priors via differential privacy. Advances in neural information processing systems (NeurIPS) (pp. 8440\u20138450)."},{"key":"6391_CR12","unstructured":"Esposito, A.R., Gastpar, M., Issa, I. (2020). Robust generalization via $$\\alpha$$\u2014Mutual information. CoRR, abs\/2001.06399."},{"key":"6391_CR13","doi-asserted-by":"crossref","unstructured":"Freund, Y. (1998). Self bounding learning algorithms. Annual conference on computational learning theory (COLT) (pp. 247\u2013258). ACM.","DOI":"10.1145\/279943.279993"},{"key":"6391_CR14","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.neucom.2019.10.105","volume":"379","author":"P Germain","year":"2020","unstructured":"Germain, P., Habrard, A., Laviolette, F., & Morvant, E. (2020). PAC-Bayes and domain adaptation. Neurocomputing, 379, 379\u2013397.","journal-title":"Neurocomputing"},{"key":"6391_CR15","doi-asserted-by":"crossref","unstructured":"Germain, P., Lacasse, A., Laviolette, F., & Marchand, M. (2009). PAC-Bayesian learning of linear classifiers. In: Annual international conference on machine learning (ICML) (Vol. 382, pp. 353\u2013360). ACM.","DOI":"10.1145\/1553374.1553419"},{"key":"6391_CR16","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.ins.2013.06.018","volume":"249","author":"M Gil","year":"2013","unstructured":"Gil, M., Alajaji, F., & Linder, T. (2013). R\u00e9nyi divergence measures for commonly used univariate continuous distributions. Information Sciences, 249, 124\u20130131.","journal-title":"Information Sciences"},{"key":"6391_CR17","unstructured":"Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep feedforward neural networks. In: International conference on artificial intelligence and statistics (AISTATS) (Vol. 9, pp. 249\u2013256). JMLR.org."},{"key":"6391_CR18","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT Press."},{"key":"6391_CR19","unstructured":"Guedj, B. (2019). A primer on PAC-Bayesian learning. CoRR, abs\/1901.05353."},{"key":"6391_CR20","unstructured":"Hardt, M., Recht, B., & Singer, Y. (2016). Train faster, generalize better: Stability of stochastic gradient descent. In: International conference on machine learning (ICML) (Vol. 48, pp. 1225\u20131234). JMLR.org."},{"key":"6391_CR21","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification.In:  IEEE international conference on computer vision (ICCV) (pp. 1026\u20131034). IEEE Computer Society.","DOI":"10.1109\/ICCV.2015.123"},{"key":"6391_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In: IEEE conference on computer vision and pattern recognition (CVPR) (pp. 770\u2013778). IEEE Computer Society.","DOI":"10.1109\/CVPR.2016.90"},{"key":"6391_CR23","unstructured":"Kingma, D., & Ba, J. (2015). Adam: A method for stochastic optimization. In: International conference on learning representations (ICLR)."},{"key":"6391_CR24","unstructured":"Krizhevsky, A. (2009). Learning multiple layers of features from tiny images (Unpublished master\u2019s thesis). University of Toronto."},{"key":"6391_CR25","unstructured":"Langford, J., & Caruana, R. (2001). (Not) bounding the true error. Advances in neural information processing systems (NIPS) (pp. 809\u2013816). MIT Press."},{"key":"6391_CR26","unstructured":"Langford, J., & Shawe-Taylor, J. (2002). PAC-Bayes & margins. Advances in neural information processing systems (NIPS) (pp. 423\u2013430). MIT Press."},{"key":"6391_CR27","unstructured":"LeCun, Y., Cortes, C., & Burges, C. (1998). The MNIST dataset of handwritten digits. Retrieved from http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"6391_CR28","unstructured":"Letarte, G., Germain, P., Guedj, B., Laviolette, F. (2019). Dichotomize and generalize: PAC-Bayesian binary activated deep neural networks. Advances in neural information processing systems (NeurIPS) (pp. 6869\u20136879)."},{"key":"6391_CR29","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.tcs.2012.10.013","volume":"473","author":"G Lever","year":"2013","unstructured":"Lever, G., Laviolette, F., & Shawe-Taylor, J. (2013). Tighter PAC-Bayes bounds through distribution-dependent priors. Theoretical Computer Science, 473, 4\u201328.","journal-title":"Theoretical Computer Science"},{"key":"6391_CR30","unstructured":"Maurer, A. (2004). A note on the PAC Bayesian theorem. CoRR, cs.LG\/0411099 ."},{"key":"6391_CR31","doi-asserted-by":"crossref","unstructured":"McAllester, D. (1998). Some PAC-Bayesian theorems. In: Annual conference on computational learning theory (COLT) (pp. 230\u2013234). ACM.","DOI":"10.1145\/279943.279989"},{"key":"6391_CR32","volume-title":"Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience","author":"V Nagarajan","year":"2019","unstructured":"Nagarajan, V., & Kolter, Z. (2019). Deterministic PAC-Bayesian generalization bounds for deep networks via generalizing noise-resilience. International conference on learning representations (ICLR): OpenReview. net."},{"key":"6391_CR33","unstructured":"Nagarajan, V., & Kolter, Z. (2019b). Uniform convergence may be unable to explain generalization in deep learning. Advances in neural information processing systems (NeurIPS) (pp. 11611\u201311622)."},{"key":"6391_CR34","volume-title":"A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks","author":"B Neyshabur","year":"2018","unstructured":"Neyshabur, B., Bhojanapalli, S., & Srebro, N. (2018). A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks. International conference on learning representations (ICLR): OpenReview.net."},{"key":"6391_CR35","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., & Chintala, S. (2019). PyTorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems (NeurIPS) (pp. 8024\u20138035)."},{"key":"6391_CR36","unstructured":"P\u00e9rez-Ortiz, M., Rivasplata, O., Shawe-Taylor, J., & Szepesv\u00e1ri, C. (2021). Tighter risk certificates for neural networks. Journal of Machine Learning Research, 22, 227:1\u2013227:40."},{"key":"6391_CR37","unstructured":"Reeb, D., Doerr, A., Gerwinn, S., & Rakitsch, B. (2018). Learning gaussian processes by minimizing PAC-Bayesian generalization bounds. Advances in neural information processing systems (NeurIPS) (pp. 3341\u20133351)."},{"key":"6391_CR38","unstructured":"Rivasplata, O., Kuzborskij, I., Szepesv\u00e1ri, C., & Shawe-Taylor, J. (2020). PACBayes analysis beyond the usual bounds. Advances in neural information processing systems (NeurIPS)."},{"key":"6391_CR39","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1162\/153244303765208377","volume":"3","author":"M Seeger","year":"2002","unstructured":"Seeger, M. (2002). PAC-Bayesian generalisation error bounds for gaussian process classification. Journal of Machine Learning Research, 3, 233\u2013269.","journal-title":"Journal of Machine Learning Research"},{"key":"6391_CR40","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019","volume-title":"Understanding machine learning - from theory to algorithms","author":"S Shalev-Shwartz","year":"2014","unstructured":"Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning - from theory to algorithms. Cambridge University Press."},{"key":"6391_CR41","doi-asserted-by":"crossref","unstructured":"Shawe-Taylor, J., & Williamson, R. (1997). A PAC analysis of a bayesian estimator. In: Annual conference on computational learning theory (COLT) (pp. 2\u20139). ACM.","DOI":"10.1145\/267460.267466"},{"key":"6391_CR42","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2015). Striving for simplicity: The all convolutional net. In: International conference on learning representations (ICLR)."},{"key":"6391_CR43","unstructured":"Thiemann, N., Igel, C., Wintenberger, O., & Seldin, Y. (2017). A strongly quasiconvex PAC-Bayesian bound. In: International conference on algorithmic learning theory (ALT) (Vol. 76, pp. 466\u2013492). PMLR."},{"issue":"11","key":"6391_CR44","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1145\/1968.1972","volume":"27","author":"L Valiant","year":"1984","unstructured":"Valiant, L. (1984). A theory of the learnable. Communications of the ACM, 27(11), 1134\u20131142.","journal-title":"Communications of the ACM"},{"issue":"7","key":"6391_CR45","doi-asserted-by":"publisher","first-page":"3797","DOI":"10.1109\/TIT.2014.2320500","volume":"60","author":"T van Erven","year":"2014","unstructured":"van Erven, T., & Harremo\u00ebs, P. (2014). R\u00e9nyi divergence and Kullback-Leibler divergence. IEEE Transactions on Information Theory, 60(7), 3797\u20133820.","journal-title":"IEEE Transactions on Information Theory"},{"key":"6391_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-3264-1","volume-title":"The nature of statistical learning theory","author":"V Vapnik","year":"2000","unstructured":"Vapnik, V. (2000). The nature of statistical learning theory. Springer."},{"key":"6391_CR47","unstructured":"Verd\u00fa, S. (2015). $$\\alpha$$-mutual information. Information theory and applications workshop (ITA) (pp. 1\u20136). IEEE."},{"key":"6391_CR48","unstructured":"Viallard, P., Vidot, G., Habrard, A., & Morvant, E. (2021). A PAC-Bayes analysis of adversarial robustness. Advances in neural information processing systems (NeurIPS) (pp. 14421\u201314433)."},{"key":"6391_CR49","unstructured":"Xiao, H., Rasul, K., & Vollgraf, R. (2017). Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. CoRR, abs\/1708.07747 ."},{"issue":"3","key":"6391_CR50","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1007\/s10994-011-5268-1","volume":"86","author":"H Xu","year":"2012","unstructured":"Xu, H., & Mannor, S. (2012). Robustness and generalization. Machine Learning, 86(3), 391\u2013423.","journal-title":"Machine Learning"},{"key":"6391_CR51","unstructured":"Zantedeschi, V., Viallard, P., Morvant, E., Emonet, R., Habrard, A., Germain, P., & Guedj, B. (2021). Learning stochastic majority votes by minimizing a PAC-Bayes generalization bound. Advances in neural information processing systems (NeurIPS) (pp. 455\u2013467)."},{"key":"6391_CR52","volume-title":"Non-vacuous generalization bounds at the ImageNet scale: a PAC-Bayesian compression approach","author":"W Zhou","year":"2019","unstructured":"Zhou, W., Veitch, V., Austern, M., Adams, R., & Orbanz, P. (2019). Non-vacuous generalization bounds at the ImageNet scale: a PAC-Bayesian compression approach. International conference on learning representations (ICLR): OpenReview.net."}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06391-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-023-06391-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-023-06391-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:04:47Z","timestamp":1728605087000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-023-06391-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,11]]},"references-count":52,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["6391"],"URL":"https:\/\/doi.org\/10.1007\/s10994-023-06391-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2023,10,11]]},"assertion":[{"value":"24 December 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}