Deep generative models are a category of machine learning models that utilizes deep neural networks to model data distributions and generate new samples. In this seminar, we first introduce our proposed framework to learn a generative model via Schrödinger Bridge, as a stochastic differential equation (SDE)-based generative model. The generative learning task can be formulated as interpolating between a reference distribution and a target distribution based on the Kullback-Leibler divergence, which can be characterized via an SDE on [0, 1] with a time-varying drift term. However, although SDE-based generative models have achieved state-of-the-art performance, they have a less efficient sampling procedure compared with other models such as generative adversarial networks. In the next part, we will discuss feasible ways to solve this problem.

5月2日
4:00pm - 5:00pm
地點
https://hkust.zoom.us/j/97557961147 (Passcode: 672570)
講者/表演者
Mr. Gefei WANG
主辦單位
Department of Mathematics
聯絡方法
付款詳情
對象
Alumni, Faculty and staff, PG students, UG students
語言
英語
其他活動
3月24日
研討會, 演講, 講座
IAS / School of Science Joint Lecture - Pushing the Limit of Nonlinear Vibrational Spectroscopy for Molecular Surfaces/Interfaces Studies
Abstract Surfaces and interfaces are ubiquitous in Nature. Sum-frequency generation vibrational spectroscopy (SFG-VS) is a powerful surface/interface selective and sub-monolayer sensitive spect...
11月22日
研討會, 演講, 講座
IAS / School of Science Joint Lecture - Leveraging Protein Dynamics Memory with Machine Learning to Advance Drug Design: From Antibiotics to Targeted Protein Degradation
Abstract Protein dynamics are fundamental to protein function and encode complex biomolecular mechanisms. Although Markov state models have made it possible to capture long-timescale protein co...