报告题目：融合范畴的分类

报 告 人：董井成

时 间：2021年10月30日（周六）下午2:30-4:30

地 点：腾讯会议，会议号请联系陈刚老师

简 介： 在本报告中，我们将首先介绍有关融合范畴的基础知识和一些有趣的例子，然后重点介绍融合范畴的分类在以下三个方向的发展现状：简单维数融合范畴的分类；低秩融合范畴的分类；简单融合法则的融合范畴的分类。

报告题目：Deep Nonparametric Estimation

报 告 人：焦雨领

时 间：2021年11月2日（周二）上午10:00-11:00

地 点：6号楼二楼报告厅

简 介： In this talk, I will present some theoretical results in deep nonparametric estimation including regression, classification and GANs

报告题目：Sampling: one application of optimal transport

报 告 人：刘旭

时 间：2021年11月2日（周二）上午9:00-10:00

地 点：6号楼二楼报告厅

简 介：We propose a relative entropy gradient sampler (REGS) for sampling from unnormalized distributions. REGS is a particle method that seeks a sequence of simple nonlinear transforms iteratively pushing the initial samples from a reference distribution into the samples from an unnormalized target distribution. To determine the nonlinear transforms at each iteration, we consider the Wasserstein gradient flow of relative entropy. This gradient flow determines a path of probability distributions that interpolates the reference distribution and the target distribution. It is characterized by an ODE system with velocity fields depending on the density ratios of the density of evolving particles and the unnormalized target density. To sample with REGS, we need to estimate the density ratios and simulate the ODE system with particle evolution. We propose a novel nonparametric approach to estimating the logarithmic density ratio using neural networks. Extensive simulation studies on challengin...