理论物理交流平台系列报告——张潘研究员

发布日期:2019-02-25 作者:    编辑:康瑶    来源:

应物理学院黄亮教授邀请,中国科学院理论物理研究所张潘研究员来我院访问,并做学术报告。欢迎广大师生届时参加!

题目:Solving Statistical Mechanics using Variational Autoregressive Networks

时间:2019年3月1日(星期五)10:30

地点:格致楼3016报告厅

Abstract: Computing free energy, estimating physical quantities, and generating uncorrelated samples are fundamental problems in statistical mechanics. In this talk I will introduce a new framework for solving the statistical mechanics problems for systems with a finite size. The approach extends the celebrated variational mean-field approaches using autoregressive networks, a neural network model which supports direct sampling and exact calculation of normalized probability of configurations. Training of the network employs the policy gradient approach in reinforcement learning, which unbiasedly estimates the gradient of variational parameters. We apply our approach to several classic systems, including 2-d Ising models, Hopfield model, Sherrington--Kirkpatrick spin glasses, and the inverse Ising model, for demonstrating its advantages over exiting variational mean-field methods.

Reference: arXiv:1809.10606, PRL in press (Editor's suggestion)

报告人简介:

张潘,本科(2004年), 博士(2009年)毕业于兰州大学,其后在法国巴黎的统计物理研究组,以及美国圣塔菲研究所做博士后研究,并于2015年就职于中科院理论物理研究所任副研究员,2019年任研究员。张潘的研究方向为统计物理与机器学习的交叉领域,近年的研究兴趣集中在统计推断问题中的统计物理理论,以及基于量子和统计物理的非监督机器学习新方法.