Dear colleagues,
We are pleased to announce that the 2025/26 season of the EURO Online Seminar Series on Operational Research and Machine Learning will start on Monday, October 6, at 16.30 CET. You can find below details on this session. Recall that the list of upcoming speakers can be found on our our website (https://euroorml.euro-online.org/), and LinkedIn: https://www.linkedin.com/company/euroorml/. , and that links to the seminars are sent by email, usually on Mondays, and are available on our website shortly before the seminar starts.
October 6, 2025, 16.30 CET
Prof Frits Spieksma, President of EURO, will open the 2025/26 season of the EURO Online Seminar Series on Operational Research and Machine Learning
Prof Daniel Kuhn, EPFL, Switzerland, will give the following talk
Title of the talk: Contextual Stochastic Bilevel Optimization
Abstract of the talk: We introduce contextual stochastic bilevel optimization (CSBO) - a stochastic bilevel optimization framework with the lower-level problem minimizing an expectation conditioned on contextual information and on the upper-level decision variable. We also assume that there may be multiple (or even infinitely many) followers at the lower level. CSBO encapsulates important applications such as meta-learning, personalized federated learning, end-to-end learning, and Wasserstein distributionally robust optimization with side information as special cases. Due to the contextual information at the lower level, existing single-loop methods for classical stochastic bilevel optimization are not applicable. We thus propose an efficient double-loop gradient method based on the Multilevel Monte-Carlo (MLMC) technique. When specialized to stochastic nonconvex optimization, the sample complexity of our method matches existing lower bounds. Our results also have important ramifications for three-stage stochastic optimization and challenge the long-standing belief that three-stage stochastic optimization is harder than classical two-stage stochastic optimization.
This seminar series is an activity of EURO, https://www.euro-online.org/. Click or tap if you trust this link." href="https://eur02.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.euro-online.org%2F&data=05%7C02%7Ctha.eco%40cbs.dk%7C8ba6b5f32e5d4929474a08dce2f502f2%7C875c414e5d004cdbb77adeae5d6ab201%7C0%7C0%7C638634789169434820%7CUnknown%7CTWFpbGZsb3d8eyJWIjoiMC4wLjAwMDAiLCJQIjoiV2luMzIiLCJBTiI6Ik1haWwiLCJXVCI6Mn0%3D%7C0%7C%7C%7C&sdata=Hlo6y7zhZQEoEt8RfR2f6iRzqI6m5pYT%2Fl61cGG%2FzWc%3D&reserved=0" target="_blank" >https://www.euro-online.org, branding the role of Operational Research in Artificial Intelligence. We have already achieved more than 2,000 colleagues registered to the mailing list, https://forms.gle/YWLb6EPKRQnQert68 . We would like to thank you very much for following our updates about the EURO Online Seminar Series on Operational Research and Machine Learning. Please circulate this link to your networks to grow even more the number of followers of this EURO instrument!
Kind regards,
The organizers of the EURO OSS on Operational Research and Machine Learning
Emilio Carrizosa, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Nuria Gómez-Vargas, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Thomas Halskov, Copenhagen Business School
Ansgar Boss Henrichsen, Copenhagen Business School
Antonio Navas Orozco, IMUS-Instituto de Matemáticas de la Universidad de Sevilla
Dolores Romero Morales, Copenhagen Business School