{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T18:10:18Z","timestamp":1773339018121,"version":"3.50.1"},"reference-count":108,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Finan. Math."],"published-print":{"date-parts":[[2026,3,31]]},"DOI":"10.1137\/24m1711650","type":"journal-article","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T08:01:31Z","timestamp":1773302491000},"page":"245-279","source":"Crossref","is-referenced-by-count":0,"title":["Time-Causal VAE: Robust Financial Time Series Generator"],"prefix":"10.1137","volume":"17","author":[{"given":"Beatrice","family":"Acciaio","sequence":"first","affiliation":[{"name":"Department of Mathematics, ETH Z\u00fcrich, 8092 Z\u00fcrich, Switzerland."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6407-2498","authenticated-orcid":true,"given":"Stephan","family":"Eckstein","sequence":"additional","affiliation":[{"name":"Department of Mathematics, University of T\u00fcbingen, 72076 T\u00fcbingen, Germany."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7289-6147","authenticated-orcid":true,"given":"Songyan","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Mathematics, ETH Z\u00fcrich, 8092 Z\u00fcrich, Switzerland."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"351","published-online":{"date-parts":[[2026,3,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.spa.2019.08.009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1214\/24-AAP2082"},{"key":"ref3","unstructured":"B. Acciaio, S. Hou, and G. Pammer, Estimating Causal Distances with Non-Causal Ones, preprint, arXiv:2506.22421, 2025."},{"key":"ref4","unstructured":"M. Arjovsky, S. Chintala, and L. Bottou, Wasserstein generative adversarial networks, in Proceedings of the 34th International Conference on Machine Learning, Vol. 70, 2017, pp. 214\u2013223."},{"key":"ref5","doi-asserted-by":"crossref","unstructured":"S. A. Assefa, D. Dervovic, M. Mahfouz, R. E. Tillman, P. Reddy, and M. Veloso, Generating synthetic data in finance: Opportunities, challenges and pitfalls, in Proceedings of the First ACM International Conference on AI in Finance, 2020, pp. 1\u20138.","DOI":"10.1145\/3383455.3422554"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00780-020-00426-3"},{"key":"ref7","first-page":"529","volume":"32","author":"Backhoff-Veraguas J.","journal-title":"Ann. Appl. Probab."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1137\/16M1080197"},{"key":"ref9","first-page":"39","volume":"20","author":"Bailey D.","year":"2017","journal-title":"J. Comput. Finance"},{"key":"ref10","first-page":"2712","volume":"20","author":"Becker S.","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","first-page":"1","volume":"26","author":"B\u00e9n\u00e9zet C.","year":"2025","journal-title":"J. Mach. Learn. Res."},{"key":"ref12","unstructured":"P. Bhowal, A. Soni, and S. Rambhatla, Why do variational autoencoders really promote disentanglement? in 41st International Conference on Machine Learning, 2024."},{"key":"ref13","unstructured":"F. Biagini, L. Gonon, and N. Walter, Universal Randomised Signatures for Generative Time Series Modelling, preprint, arXiv:2406.10214, 2024."},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1214\/18-AAP1423"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1162\/089976698300017953"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1086\/260062"},{"key":"ref17","doi-asserted-by":"crossref","unstructured":"S. R. Bowman, L. Vilnis, O. Vinyals, A. M. Dai, R. Jozefowicz, and S. Bengio, Generating Sentences from a Continuous Space, preprint, arXiv:1511.06349, 2015.","DOI":"10.18653\/v1\/K16-1002"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/BF00537538"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3632431"},{"key":"ref20","unstructured":"C. P. Burgess, I. Higgins, A. Pal, L. Matthey, N. Watters, G. Desjardins, and A. Lerchner, Understanding Disentangling in \\(\\beta\\)-VAE, preprint, arXiv:1804.03599, 2018."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111079"},{"key":"ref22","volume":"31","author":"Chen R. T.","year":"2018","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref23","unstructured":"X. Chen, D. P. Kingma, T. Salimans, Y. Duan, P. Dhariwal, J. Schulman, I. Sutskever, and P. Abbeel, Variational lossy autoencoder, in Proceedings of the International Conference on Learning Representations (ICLR), 2016."},{"key":"ref24","first-page":"1","volume":"23","author":"Chevyrev I.","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","unstructured":"R. Child, Very deep VAEs generalize autoregressive models and can outperform them on images, in Proceedings of the 9th International Conference on Learning Representations (ICLR). Virtual Conference, 2021."},{"key":"ref26","volume":"28","author":"Chung J.","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1515\/strm-2025-0004"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70679-1"},{"key":"ref29","doi-asserted-by":"crossref","unstructured":"A. Coletta, J. Jerome, R. Savani, and S. Vyetrenko, Conditional generators for limit order book environments: Explainability, challenges, and robustness, in Proceedings of the Fourth ACM International Conference on AI in Finance, 2023, pp. 27\u201335.","DOI":"10.1145\/3604237.3626854"},{"key":"ref30","doi-asserted-by":"crossref","unstructured":"A. Coletta, M. Prata, M. Conti, E. Mercanti, N. Bartolini, A. Moulin, S. Vyetrenko, and T. Balch, Towards realistic market simulations:\u00a0A generative adversarial networks approach, in Proceedings of the Second ACM International Conference on AI in Finance, 2021, pp. 1\u20139.","DOI":"10.1145\/3490354.3494411"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1080\/713665670"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"R. Cont, M. Cucuringu, J. Kochems, and F. Prenzel, Limit Order Book Simulation with Generative Adversarial Networks, http:\/\/dx.doi.org\/10.2139\/ssrn.4512356, 2023.","DOI":"10.2139\/ssrn.4512356"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"R. Cont, M. Cucuringu, R. Xu, and C. Zhang, Tail-GAN: Learning to simulate tail risk scenarios, Manag. Sci. (2025).","DOI":"10.1287\/mnsc.2023.00936"},{"key":"ref34","unstructured":"F. de Meer Pardo, Enriching Financial Datasets with Generative Adversarial Networks,\u00a0M.S.\u00a0thesis, Delft University of Technology, 2019."},{"key":"ref35","unstructured":"A. Desai, C. Freeman, Z. Wang, and I. Beaver, TimeVAE:A Variational Auto-Encoder for Multivariate Time Series Generation, preprint, arXiv:2111.08095, 2021."},{"key":"ref36","doi-asserted-by":"crossref","unstructured":"I. Deshpande, Y.T. Hu, R. Sun, A. Pyrros, N. Siddiqui, S. Koyejo, Z. Zhao, D. Forsyth, and A. G. Schwing, Max-sliced Wasserstein distance and its use for gans, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 10648\u201310656.","DOI":"10.1109\/CVPR.2019.01090"},{"key":"ref37","unstructured":"N. Dilokthanakul, P. A. Mediano, M. Garnelo, M. C. Lee, H. Salimbeni, K. Arulkumaran, and M. Shanahan, Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders, preprint, arXiv:1611.02648, 2016."},{"key":"ref38","unstructured":"L. Dinh, J. Sohl-Dickstein, and S. Bengio, Density Estimation Using Real NVP, preprint, arXiv:1605.08803, 2016."},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"F. Eckerli and J. Osterrieder, Generative Adversarial Networks in Finance: An Overview, preprint, arXiv:2106.06364, 2021.","DOI":"10.2139\/ssrn.3864965"},{"key":"ref40","unstructured":"D. Efimov, D. Xu, L. Kong, A. Nefedov, and A. Anandakrishnan, Using Generative Adversarial Networks to Synthesize Artificial Financial Datasets, preprint, arXiv:2002.02271, 2020."},{"key":"ref41","unstructured":"L. Ericson, X. Zhu, X. Han, R. Fu, S. Li, S. Guo, and P. Hu, Deep Generative Modeling for Financial Time Series with Application in VaR: A Comparative Review, preprint, arXiv:2401.10370, 2024."},{"key":"ref42","unstructured":"C. Esteban, S. Hyland, and G. R\u00e4tsch, Real-Valued (Medical) Time Series Generation with Recurrent Conditional GANs, preprint, arXiv:1706.02633, 2017."},{"key":"ref43","first-page":"1","volume":"22","author":"Flamary R.","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1515\/9783110218053"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1080\/1350486X.2023.2224354"},{"key":"ref46","unstructured":"W. Fu, A. Hirsa, and J. Osterrieder, Simulating Financial Time Series Using Attention, arXiv:2207.00493, 2022."},{"key":"ref47","doi-asserted-by":"crossref","unstructured":"I. Gatopoulos, M. Stol, and J. M. Tomczak, Super-Resolution Variational Auto-Encoders, preprint, arXiv:2006.05218, 2020.","DOI":"10.3390\/e23060747"},{"key":"ref48","unstructured":"N. Gigli, On the Geometry of the Space of Probability Measures in \\(\\mathbb{R}^{n}\\) Endowed with the Quadratic Optimal Transport Distance, Ph.D. thesis, Scuola Normale Superiore, 2008."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1561\/2200000089"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-018-1352-7"},{"key":"ref51","volume":"27","author":"Goodfellow I.","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref52","first-page":"723","volume":"13","author":"Gretton A.","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2023.2221281"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4412434"},{"key":"ref55","unstructured":"C. Herrera, F. Krach, P. Ruyssen, and J. Teichmann, Optimal Stopping via Randomized Neural Networks, preprint, arXiv:2104.13669, 2021."},{"key":"ref56","unstructured":"I. Higgins, L. Matthey, A. Pal, C. Burgess, X. Glorot, M. Botvinick, S. Mohamed, and A. Lerchner, Beta-VAE: Learning basic visual concepts with a constrained variational framework, in International Conference on Learning Representations, 2016."},{"key":"ref57","first-page":"104775","author":"Hou S.","year":"2025","journal-title":"Stoch. Process. Their Appl."},{"key":"ref58","unstructured":"H. Huang, M. Chen, and X. Qiao, Generative learning for financial time series with irregular and scale-invariant patterns, in 12th International Conference on Learning Representations, 2024."},{"key":"ref59","unstructured":"H. Hultin, Generative Models of Limit Order Books, Ph.D. thesis, KTH Royal Institute of Technology, 2021."},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2023.2205583"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08459-3"},{"key":"ref62","volume":"36","author":"Issa Z.","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref63","first-page":"12104","volume":"33","author":"Karras T.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref64","unstructured":"P. Kidger, On Neural Differential Equations Ph.D. thesis, Oxford University, 2021."},{"key":"ref65","unstructured":"P. Kidger, J. Foster, X. Li, and T. J. Lyons, Neural SDEs as infinite-dimensional GANs, in International Conference on Machine Learning, PMLR, 2021, pp. 5453\u20135463."},{"key":"ref66","unstructured":"D. P. Kingma and M. Welling, Auto-encoding variational Bayes, in Second International Conference on Learning Representations, 2014."},{"key":"ref67","volume":"32","author":"Kolouri S.","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref68","doi-asserted-by":"crossref","unstructured":"A. Kondratyev and C. Schwarz, The market generator, SSRN Electron. J. (2019), https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=3384948.","DOI":"10.2139\/ssrn.3384948"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2020.1790635"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/07362994.2017.1422747"},{"key":"ref71","volume":"30","author":"Li C.-L.","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1111\/1467-9965.00100"},{"key":"ref73","doi-asserted-by":"crossref","unstructured":"J. Li, X. Wang, Y. Lin, A. Sinha, and M. Wellman, Generating realistic stock market order streams, in Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34, 2020, pp. 727\u2013734.","DOI":"10.1609\/aaai.v34i01.5415"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1111\/mafi.12423"},{"key":"ref75","doi-asserted-by":"crossref","unstructured":"Y. Liu, S. Wijewickrema, A. Li, C. Bester, S. O\u2019Leary and J. Bailey, Time-transformer:\u00a0Integrating local and global features for Better Time Series Generation (Extended Version), in Proceedings of the 2024 SIAM International Conference on Data Mining (SDM), Society for Industrial and Applied Mathematics, 2024, pp. 325\u2013333.","DOI":"10.1137\/1.9781611978032.37"},{"key":"ref76","volume":"36","author":"Lou H.","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref77","unstructured":"Y. Lu, M. Shen, H. Wang, X. Wang, C. van Rechem, and W. Wei, Machine Learning for Synthetic Data Generation: A Review, preprint, arXiv:2302.04062, 2023."},{"key":"ref78","unstructured":"E. Mathieu, T. Rainforth, N. Siddharth, and Y. W. Teh, Disentangling disentanglement in variational autoencoders, in International Conference on Machine Learning, 2019, pp. 4402\u20134412."},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-780850-5.50052-6"},{"key":"ref80","doi-asserted-by":"crossref","unstructured":"P. Nagy, S. Frey, S. Sapora, K. Li, A. Calinescu, S. Zohren, and J. Foerster, Generative AIfor end-to-end limit order book modelling: A token-level autoregressive generative model of message flow using a deep state space network, in Proceedings of the Fourth ACM International Conference on AI in Finance, 2023, pp. 91\u201399.","DOI":"10.1145\/3604237.3626898"},{"key":"ref81","doi-asserted-by":"crossref","unstructured":"H. Ni, L. Szpruch, M. Sabate-Vidales, B. Xiao, M. Wiese, and S. Liao, Sig-Wasserstein GANs for time series generation, in Proceedings of the Second ACM International Conference on AI in Finance, 2021, pp. 1\u20138.","DOI":"10.1145\/3490354.3494393"},{"key":"ref82","first-page":"28179","volume":"35","author":"Nietert S.","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref83","volume-title":"Introduction to Entropic Optimal Transport","author":"Nutz M.","year":"2021"},{"key":"ref84","unstructured":"M. I. \u00d6zyar, Learning the Limit Order Book: A Comprehensive Mix between Stochastic and Machine Learning Models for Generation and Prediction, preprint, https:\/\/arxiv.org\/html\/2505.02139v1, 2021."},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1214\/23-ECP572"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1137\/110825054"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-08843-3"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s10589-015-9758-0"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1137\/15M1043376"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1137\/110857088"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1007\/s10287-021-00415-7"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-4869-3"},{"key":"ref93","unstructured":"D. J. Rezende and F. Viola, Taming VAEs, preprint, arXiv:1810.00597, 2018."},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2023.128899"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1111\/1540-6261.00453"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/BF00532240"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1142\/S2705109925500099"},{"key":"ref98","unstructured":"J. Stanczuk, C. Etmann, L. M. Kreusser, and C.B. Sch\u00f6nlieb, Wasserstein GANs Work because They Fail (to Approximate the Wasserstein Distance), preprint, arXiv:2103.01678, 2021."},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2019.121261"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1002\/0471771457"},{"key":"ref101","doi-asserted-by":"crossref","unstructured":"H. Thanh-Tung and T. Tran, Catastrophic forgetting and mode collapse in GANs, in 2020 International Joint Conference on Neural Networks, 2020, pp. 1\u201310.","DOI":"10.1109\/IJCNN48605.2020.9207181"},{"key":"ref102","unstructured":"J. Tomczak and M. Welling, VAE with a VampPrior, in International Conference on Artificial Intelligence and Statistics, P2018, pp. 1214\u20131223."},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2023.2299466"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1080\/14697688.2020.1730426"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3980817"},{"key":"ref106","first-page":"8798","volume":"33","author":"Xu T.","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref107","doi-asserted-by":"crossref","unstructured":"X. Yang, H. Zhang, G. Qi, and J. Cai, Causal attention for vision-language tasks, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 9847\u20139857.","DOI":"10.1109\/CVPR46437.2021.00972"},{"key":"ref108","volume":"32","author":"Yoon J.","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."}],"container-title":["SIAM Journal on Financial Mathematics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T08:02:46Z","timestamp":1773302566000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1711650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,12]]},"references-count":108,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,3,31]]}},"alternative-id":["10.1137\/24M1711650"],"URL":"https:\/\/doi.org\/10.1137\/24m1711650","relation":{},"ISSN":["1945-497X"],"issn-type":[{"value":"1945-497X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,12]]}}}