{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T15:05:04Z","timestamp":1780067104103,"version":"3.54.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:00:00Z","timestamp":1766966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Korea Advanced Institute of Science and Technology"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:bold>Conditional Generative Adversarial Networks (cGANs)<\/jats:bold>\n                    provide a flexible framework for learning conditional distributions, but they suffer from two fundamental challenges: the scarcity of conditional samples and the curse of dimensionality in the image space. In this work, we address both issues by introducing\n                    <jats:bold>Vicinal Estimation (VE)<\/jats:bold>\n                    into the cGAN framework and analyzing it through Barron-space discriminators. VE alleviates the lack of conditional samples by coupling nearby labels via an auxiliary sampling distribution, effectively transforming the problem into a collection of unconditional GANs in the vicinal label space. Meanwhile, the Barron-space analysis yields a dimension-independent generalization bound that holds irrespective of the image dimension, and we show how this bound transfers from VE conditionals back to the original conditional distributions. We develop\n                    <jats:bold>VE-cGAN<\/jats:bold>\n                    , a practical instantiation of this idea, and demonstrate through experiments on benchmark datasets that it achieves improved perceptual quality and label consistency compared with baselines. Our theoretical and empirical findings together highlight VE as a principled and effective approach to overcoming the lack of conditional samples and the curse of dimensionality in conditional generative modeling.\n                  <\/jats:p>","DOI":"10.1007\/s10994-025-06953-4","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:38:07Z","timestamp":1767033487000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["VE-cGAN: Improved Generalization Analysis of Conditional Generative Adversarial Networks Using Vicinal Estimation"],"prefix":"10.1007","volume":"115","author":[{"given":"Ki Joung","family":"Jang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ganguk","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,29]]},"reference":[{"key":"6953_CR1","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In: International Conference on Machine Learning, pp. 214\u2013223. PMLR."},{"key":"6953_CR2","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2019). Large scale GAN training for high fidelity natural image synthesis. In: 7th International Conference on Learning Representations (ICLR). OpenReview.net, New Orleans, LA, USA. https:\/\/openreview.net\/forum?id=B1xsqj09Fm"},{"key":"6953_CR3","unstructured":"Chapelle, O., Weston, J., Bottou, L., & Vapnik, V. (2000). Vicinal risk minimization. In: Advances in Neural Information Processing Systems (NeurIPS), vol. 13. MIT Press, Cambridge, MA, USA."},{"issue":"4","key":"6953_CR4","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/BF02551274","volume":"2","author":"G Cybenko","year":"1989","unstructured":"Cybenko, G. (1989). Approximation by superpositions of a sigmoidal function. Mathematics of Control, Signals, and Systems, 2(4), 303\u2013314. https:\/\/doi.org\/10.1007\/BF02551274","journal-title":"Mathematics of Control, Signals, and Systems"},{"issue":"7","key":"6953_CR5","doi-asserted-by":"publisher","first-page":"8143","DOI":"10.1109\/TPAMI.2022.3228915","volume":"45","author":"X Ding","year":"2023","unstructured":"Ding, X., Wang, Y., Xu, Z., Welch, W. J., & Wang, Z. J. (2023). Continuous conditional generative adversarial networks: Novel empirical losses and label input mechanisms. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(7), 8143\u20138158. https:\/\/doi.org\/10.1109\/TPAMI.2022.3228915","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"6953_CR6","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1109\/JSAIT.2020.2991375","volume":"1","author":"S Feizi","year":"2020","unstructured":"Feizi, S., Farnia, F., Ginart, T., & Tse, D. (2020). Understanding gans in the LQG setting: Formulation, generalization and stability. IEEE Journal on Selected Areas in Information Theory, 1(1), 304\u2013311. https:\/\/doi.org\/10.1109\/JSAIT.2020.2991375","journal-title":"IEEE Journal on Selected Areas in Information Theory"},{"key":"6953_CR7","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.1109\/TIFS.2023.3288426","volume":"19","author":"W Feng","year":"2024","unstructured":"Feng, W., Xu, N., Zhang, T., Wu, B., & Zhang, Y. (2024). Robust and generalized physical adversarial attacks via meta-gan. IEEE Transactions on Information Forensics and Security, 19, 1112\u20131125. https:\/\/doi.org\/10.1109\/TIFS.2023.3288426","journal-title":"IEEE Transactions on Information Forensics and Security"},{"issue":"78","key":"6953_CR8","first-page":"1","volume":"22","author":"R Flamary","year":"2021","unstructured":"Flamary, R., Courty, N., Gramfort, A., Alaya, M. Z., Boisbunon, A., Chambon, S., Chapel, L., Corenflos, A., Fatras, K., Fournier, N., Gautheron, L., Gayraud, N. T. H., Janati, H., Rakotomamonjy, A., Redko, I., Rolet, A., Schutz, A., Seguy, V., Sutherland, D. J., & Vayer, T. (2021). Pot: Python optimal transport. Journal of Machine Learning Research, 22(78), 1\u20138.","journal-title":"Journal of Machine Learning Research"},{"issue":"11","key":"6953_CR9","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2020). Generative adversarial networks. Communications of the ACM, 63(11), 139\u2013144.","journal-title":"Communications of the ACM"},{"issue":"2","key":"6953_CR10","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s10994-020-05929-w","volume":"110","author":"H Gouk","year":"2021","unstructured":"Gouk, H., Frank, E., Pfahringer, B., & Cree, M. J. (2021). Regularisation of neural networks by enforcing lipschitz continuity. Machine Learning, 110(2), 393\u2013416.","journal-title":"Machine Learning"},{"key":"6953_CR11","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017). Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: Guyon, I., Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, pp. 6626\u20136637."},{"issue":"12","key":"6953_CR12","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","volume":"43","author":"T Karras","year":"2021","unstructured":"Karras, T., Laine, S., & Aila, T. (2021). A style-based generator architecture for generative adversarial networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 43(12), 4217\u20134228. https:\/\/doi.org\/10.1109\/TPAMI.2020.2970919","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"6953_CR13","unstructured":"Lei, Q., Lee, J. D., Dimakis, A., & Daskalakis, C. (2020). SGD learns one-layer networks in wgans. In: Proceedings of the 37th International Conference on Machine Learning, ICML 2020, 13-18 July 2020, Virtual Event. Proceedings of Machine Learning Research, vol. 119, pp. 5799\u20135808. PMLR, Online. http:\/\/proceedings.mlr.press\/v119\/lei20b.html"},{"key":"6953_CR14","unstructured":"Li, P., Li, Z., Zhang, H., & Bian, J. (2023). On the generalization properties of diffusion models. In: Thirty-seventh Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=hCUG1MCFk5."},{"key":"6953_CR15","unstructured":"Mirza, M., & Osindero, S. (2014). Conditional generative adversarial nets. arXiv preprint arXiv:1411.1784."},{"issue":"3","key":"6953_CR16","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1109\/LSP.2012.2227726","volume":"20","author":"A Mittal","year":"2013","unstructured":"Mittal, A., Soundararajan, R., & Bovik, A. C. (2013). Making a \u201ccompletely blind\u2019\u2019 image quality analyzer. IEEE Signal Processing Letters, 20(3), 209\u2013212. https:\/\/doi.org\/10.1109\/LSP.2012.2227726","journal-title":"IEEE Signal Processing Letters"},{"key":"6953_CR17","unstructured":"Miyato, T., & Koyama, M. (2018). cgans with projection discriminator. In: 6th International Conference on Learning Representations (ICLR). OpenReview.net, Vancouver, BC, Canada. https:\/\/openreview.net\/forum?id=ByS1VpgRZ."},{"key":"6953_CR18","unstructured":"Miyato, T., Kataoka, T., Koyama, M., & Yoshida, Y. (2018). Spectral normalization for generative adversarial networks. In: 6th International Conference on Learning Representations (ICLR). OpenReview.net, Vancouver, BC, Canada. https:\/\/openreview.net\/forum?id=B1QRgziT-."},{"key":"6953_CR19","unstructured":"Odena, A., Olah, C., & Shlens, J. (2017). Conditional image synthesis with auxiliary classifier gans. In: Proceedings of the 34th International Conference on Machine Learning (ICML). Proceedings of Machine Learning Research, vol. 70, pp. 2642\u20132651. PMLR, Sydney, NSW, Australia. http:\/\/proceedings.mlr.press\/v70\/odena17a.html"},{"key":"6953_CR20","unstructured":"Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In: Bengio, Y., LeCun, Y. (eds.) 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2-4, 2016, Conference Track Proceedings. arXiv:1511.06434"},{"key":"6953_CR21","first-page":"239","volume-title":"Neural networks: Tricks of the Trade, This Book Is an Outgrowth of a 1996 NIPS Workshop","author":"P Simard","year":"1998","unstructured":"Simard, P., LeCun, Y., Denker, J. S., & Victorri, B. (1998). Transformation invariance in pattern recognition-tangent distance and tangent propagation. Neural networks: Tricks of the Trade, This Book Is an Outgrowth of a 1996 NIPS Workshop (pp. 239\u201327). Springer."},{"key":"6953_CR22","unstructured":"Weed, J., & Bach, F. R. (2017). Sharp asymptotic and finite-sample rates of convergence of empirical measures in wasserstein distance. Bernoulli."},{"key":"6953_CR23","doi-asserted-by":"crossref","unstructured":"Weinan, E., Ma, C., & Wu, L. (2021). The barron space and the flow-induced function spaces for neural network models. Constructive Approximation 55, 369\u2013406.","DOI":"10.1007\/s00365-021-09549-y"},{"key":"6953_CR24","unstructured":"Wu, S., Dimakis, A. G., & Sanghavi, S. (2019). Learning distributions generated by one-layer relu networks. In: Wallach, H.M., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E.B., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, December 8-14, 2019, Vancouver, BC, Canada, 8105\u20138115."},{"key":"6953_CR25","doi-asserted-by":"crossref","unstructured":"Xu, N., Feng, W., Zhang, T., & Zhang, Y. (2024). FD-GAN: Generalizable and robust forgery detection via generative adversarial networks.\u00a0International Journal of Computer Vision","DOI":"10.1007\/s11263-024-02136-1"},{"key":"6953_CR26","doi-asserted-by":"crossref","unstructured":"Yang, H., & Weinan, E. (2021). Generalization Error of GAN from the Discriminator\u2019s Perspective.","DOI":"10.1007\/s40687-021-00306-y"},{"key":"6953_CR30","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Song, Y., & Qi, H. (2017). Age progression\/regression by conditional adversarial autoencoder. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4352\u20134360. IEEE Computer Society, Honolulu, HI, USA. https:\/\/doi.org\/10.1109\/CVPR.2017.463.","DOI":"10.1109\/CVPR.2017.463"},{"key":"6953_CR27","unstructured":"Zhang, H., Ciss\u00e9, M., Dauphin, Y. N., & Lopez-Paz, D. (2018). mixup: Beyond empirical risk minimization. In: 6th International Conference on Learning Representations (ICLR). OpenReview.net, Vancouver, BC, Canada. https:\/\/openreview.net\/forum?id=r1Ddp1-Rb."},{"key":"6953_CR28","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., & Odena, A. (2019). Self-attention generative adversarial networks. In: Proceedings of the 36th International Conference on Machine Learning. ICML\u201919, vol. 97, pp. 7354\u20137363. PMLR, ???."},{"key":"6953_CR29","unstructured":"Zhang, L., Deng, Z., Kawaguchi, K., Ghorbani, A., & Zou, J. (2021). How does mixup help with robustness and generalization?."},{"key":"6953_CR31","first-page":"7559","volume":"33","author":"S Zhao","year":"2020","unstructured":"Zhao, S., Liu, Z., Lin, J., Zhu, J.-Y., & Han, S. (2020). Differentiable augmentation for data-efficient gan training. Advances in Neural Information Processing Systems, 33, 7559\u20137570.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"6953_CR32","doi-asserted-by":"publisher","first-page":"17033","DOI":"10.1609\/aaai.v38i15.29647","volume":"38","author":"Y Zhao","year":"2024","unstructured":"Zhao, Y., Wu, J., Han, Y., Liu, J., Jin, Y., & Lu, C. (2024). Ccdpm: A continuous conditional diffusion probabilistic model for image generation. Proceedings of the AAAI Conference on Artificial Intelligence, 38, 17033\u201317041. https:\/\/doi.org\/10.1609\/aaai.v38i15.29647","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06953-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06953-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06953-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T14:05:28Z","timestamp":1769781928000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06953-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,29]]},"references-count":32,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1]]}},"alternative-id":["6953"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06953-4","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,29]]},"assertion":[{"value":"5 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 December 2025","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 declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing Interests"}},{"value":"The authors affirm that the manuscript represents original work, has not been previously published, and is not currently under consideration for publication elsewhere. The authors acknowledge that any ethical considerations, including obtaining necessary approvals and permissions for data collection and analysis, have been addressed and fulfilled according to the guidelines and regulations applicable to the research.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"The authors give consent for the publication of identifiable details, including our research findings.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for Publication"}}],"article-number":"14"}}