- 演讲人： Liu Qiang（Computer Science at UT Austin）
- 时间：2022年11月11日 周五上午10:00
- 地点：腾讯会议 ID：417-265-416
- 主办单位：浙江大学数据科学研究中心
In this talk, I will show you that the problem can be addressed with a pretty simple algorithm. This algorithm, called rectified flow, learns an ordinary differential equation (ODE) model to transfer between the two distributions by following straight paths as much as possible. The algorithm only requires solving a sequence of nonlinear least squares optimization problems, which guarantees to yield monotonically non-increasing couplings w.r.t. all convex transport costs. The straight paths are special and preferred because they are the shortest paths between two points, and can be simulated exactly without time discretization, yielding computationally efficient models. In practice, the ODE models learned by our method can generate high quality images with a single discretization step, which is a significant speedup over existing diffusion generative models. Moreover, with a proper modification, our method can be used to solve the optimal transport problems on high dimensional continuous distributions, a challenging problem for which no well accepted efficient algorithms exist.
More information of the method can be found here https://www.cs.utexas.edu/~lqiang/rectflow/html/intro
Speaker Bio: Qiang Liu is an assistant professor of Computer Science at UT Austin leading the Statistical Learning & AI Group. His research interests cover broad areas of machine learning and statistical inference, with a particular focus on developing novel mathematical methodologies to address emerging practical challenges.