Machine Learning and Friends Lunch: Agustinus Kristiadi, Probabilistic Inference and Decision-Making With and For Foundation Models
Content
Speaker
Abstract
Probabilistic inference is a compelling framework for capturing our belief about an unknown given observations. Central in this paradigm are probabilistic models and approximate inference methods. The former models one’s prior belief and encodes the data, while the latter produces posterior distributions based on the former. In the era of large-scale neural networks and foundation models, leveraging them in probabilistic modeling or improving them using probabilistic inference is challenging due to their sheer size. In this talk, I will discuss recent works in (i) developing efficient probabilistic models with and for large foundation models, (ii) leveraging the resulting powerful, calibrated beliefs to improve decision-making and planning, and (iii) applying the resulting probabilistic decision-making/planning systems for improving scientific discovery, and improving the neural networks themselves.
Bio
Agustinus Kristiadi is a postdoctoral fellow at the Vector Institute and previously obtained his PhD from the University of Tuebingen in Germany. His research interests are in probabilistic inference with large-scale neural networks, decision-making under uncertainty, and their applications in broader scientific fields such as chemistry. His work has been recognized in the form of a best PhD thesis award and multiple spotlight papers from flagship machine learning conferences. In addition to his research, his contributions to the broader scientific society include mentoring underrepresented students in Canada under the IBET PhD Project and actively contributing to the open-source community.