[ML Seminar] Machine Learning Seminar, 10/9 at 13:30: Christian Naesseth, "SDE Matching: Scalable Variational Inference for Stochastic Differential Equations"

[Louis Ohl]

Welcome to an IDA Machine Learning Seminar on Wednesday, September  10 at 13:30 in Alan Turing
SDE Matching: Scalable Variational Inference for Stochastic Differential Equations
Christian Naesseth<https://naesseth.github.io/>, University of Amsterdam
Elemental AI | Christian A. Naesseth<https://naesseth.github.io/>
CAN Lab, Informatics Institute, University of AmsterdamI am an Assistant Professor of Machine Learning at the University of Amsterdam, a member of the Amsterdam Machine Learning Lab, the lab manager of the UvA-Bosch Delta Lab 2, and an ELLIS member. My research interests span generative modeling, uncertainty quantification, reasoning, and machine learning, as well as their application to the ...
naesseth.github.io
Abstract: The Latent Stochastic Differential Equation (SDE) is a powerful tool for time series and sequence modeling. However, training Latent SDEs typically relies on adjoint sensitivity methods, which depend on simulation, discretisation, and backpropagation through approximate SDE solutions, which limit scalability. In this work, we propose SDE Matching, a new simulation- and discretisation-free method for training Latent SDEs. Inspired by modern Score- and Flow Matching algorithms for learning generative dynamics, we extend these ideas to the domain of stochastic dynamics for time series and sequence modeling, eliminating the need for costly numerical simulations. Our results demonstrate that SDE Matching achieves performance comparable to adjoint sensitivity methods while drastically reducing computational complexity.
Location: Alan Turing, https://www.ida.liu.se/department/location/search.en.shtml?keyword=alan

------------------
The list of future seminars in the series is available at:
https://stima.gitlab-pages.liu.se/ml-seminars/
You can subscribe to the seminar series' calendar using this ics link: https://outlook.office365.com/owa/calendar/4d811ae47ce446f58d11a7c2f50a7ed8@ad.liu.se/0f5253d7bc7841248c71eb4c28eb2d668927992292494627279/calendar.ics


--
Louis Ohl
Postdoc
louis.ohl at liu.se

Linköping University
IDA / STIMA
B-Huset, 2A:445
Webpage<https://oshillou.github.io/>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.liu.se/pipermail/ml-seminars/attachments/20250827/d1f1e012/attachment.htm>