- This event has passed.
ESE Fall Seminar – “Deep Latent Variable Models for Compression and Natural Science”
October 10 at 11:00 AM - 12:00 PM
Latent variable models have been an integral part of probabilistic machine learning, ranging from simple mixture models to variational autoencoders to powerful diffusion probabilistic models at the center of recent media attention. Perhaps less well-appreciated is the intimate connection between latent variable models and data compression, and the potential of these models for advancing natural science. This talk will explore these topics. I will begin by showcasing connections between variational methods and the theory and practice of neural data compression. On the applied side, variational methods lead to machine-learned compressors of data such as images and videos and offer principled techniques for enhancing their compression performance, as well as reducing their decoding complexity. On the theory side, variational methods also provide scalable bounds on the fundamental compressibility of real-world data, such as images and particle physics data. Lastly, I will also delve into applications, where I show how deep latent variable models allow solving challenging inverse problems in weather and climate modeling tasks.
Stephan Mandt
Associate Professor of Computer Science and Statistics, UC Irvine
Stephan Mandt is an Associate Professor of Computer Science and Statistics at the University of California, Irvine. His research centers on deep generative modeling, uncertainty quantification, neural data compression, and AI for science. Previously, he led the machine learning group at Disney Research in Pittsburgh and Los Angeles and held postdoctoral positions at Princeton and Columbia University. Stephan holds a Ph.D. in Theoretical Physics, supported by the German National Merit Scholarship. He is furthermore a recipient of the NSF CAREER Award, the UCI ICS Mid-Career Excellence in Research Award, the German Research Foundation’s Mercator Fellowship, a Kavli Fellow of the U.S. National Academy of Sciences, a member of the ELLIS Society, and a former visiting researcher at Google Brain. His research is currently supported by NSF, DARPA, IARPA, DOE, Disney, Intel, and Qualcomm. Stephan is an Action Editor of the Journal of Machine Learning Research and Transaction on Machine Learning Research, held tutorials at NeurIPS, AAAI, and UAI, served as (Senior) Area Chair for NeurIPS, ICML, AAAI, and ICLR, and as Program Chair for AISTATS 2024. He currently serves as General Chair for AISTATS 2025.