Participate remotely via this Zoom link: https://berkeley.zoom.us/j/365562923.
Abstract: Of all machine learning methods, generative models are particularly interesting for scientific applications because of their probabilistic nature and ability to fit complex data and probability distributions. However, in their vanilla forms, generative models have a number of shortcomings and failure modes which can be a hindrance to their application: they can be difficult to train on high dimensional data, and they can fail in crucial tasks such as outlier detection or the generation of realistic artificial data. In my talk, I am going to explore the reasons for these failures and propose new generative models and generative model based approaches that are robust to these shortcomings. The proposed approaches are easy to train and validate, numerically stable, and do not require fine-tuning. They should thus be particularly fitted for scientific applications. I will demonstrate how these approaches can be used for scientifically relevant tasks such as realistic data generation and outlier detection.
Full details about this meeting will be posted here: https://bids.github.io/MLStatsForum/.
The Machine Learning and Science Forum (formerly the Berkeley Statistics and Machine Learning Forum) meets biweekly to discuss current applications across a wide variety of research domains in the physical sciences and beyond. Hosted by UC Berkeley Physics Professor and BIDS Senior Fellow Uros Seljak, these active sessions bring together domain scientists, statisticians, and computer scientists who are either developing state-of-the-art methods or are interested in applying these methods in their research. To receive email notifications about upcoming meetings, or to request more information, please contact firstname.lastname@example.org. All interested members of the UC Berkeley and Berkeley Lab communities are welcome and encouraged to attend.
Vanessa Böhm is currently a postdoctoral fellow at Berkeley Center for Cosmological Physics (BCCP). Her research focuses on developing machine learning methods that are suitable and specifically designed for scientific applications. As a cosmologist, her expertise lies in weak gravitational lensing of galaxies and the cosmic microwave background. Her research interests include how to optimally extract signals from high-dimensional, non-Gaussian data and the development and applications of differentiable simulations.