IDS Guest Seminar - by Dr Sulin Liu from MIT
Speaker: Dr Sulin Liu, Postdoctoral Researcher, Massachusetts Institute of Technology
Venue: HKU IDS, P307, Graduate House / Zoom
Mode: Hybrid. Seats for on-site participants are limited. A confirmation email will be sent to participants who have successfully registered.
Probabilistic models provide a powerful framework for modeling diverse data distributions encountered in the real world. These models have found extensive applications in ML-driven knowledge exploration and discovery, including: 1) sequential experiment design and optimization using probabilistic surrogate models like Gaussian processes, and 2) generation of novel designs through generative models. However, a key challenge hindering the application of probabilistic models in real-world scenarios is the lack of scalable solutions that maintain their expressive power. This talk will explore how to overcome this challenge by leveraging the concept of “amortization” through deep neural networks.
First, I will demonstrate how to accelerate the identification of Gaussian process hyperparameters (the major computational bottleneck) by training a single neural network to “amortize” this computationally expensive process across various zero-shot tasks. In the second part, a novel class of generative models will be introduced for flexible and scalable modeling of discrete objects, achieved by learning a neural network to approximate the marginal probability.
Dr Sulin Liu is a postdoctoral researcher at MIT working with Rafael Gómez-Bombarelli on machine learning for accelerating science discovery. He received his PhD in Electrical and Computer Engineering from Princeton University, advised by Ryan Adams and Peter Ramadge. His PhD research focuses on developing deep-learning-enabled probabilistic inference and generative models for knowledge discovery. He has also worked as a research intern at Meta Research Adaptive Experimentation team, mentored by Ben Letham and Eytan Bakshy. Prior to his PhD, Sulin received his bachelor’s degree in Electrical Engineering from National University of Singapore.
For information, please contact: