讲座题目：Approximation to stochastic variance reduced gradient algorithms by stochastic differential delay equations
主 讲 人：骆顺龙
讲座时间：2022年10月18日（周二），15:00-16:00
地点：
线下：综合楼644会议室
线上：腾讯会议 ID 693-815-084
主讲人简介：
徐礼虎，现为澳门大学副教授，主要研究方向为随机分析，极限定理，斯坦因方法等。目前在Annals of Statistics, Probability Theory and Related Fields, Annals of Applied Probability, Bernoulli, Journal of Functional Analysis, Stochastic Processes and Their Applications等杂志发表40余篇论文。
讲座摘要：
Stochastic variance reduced gradient (SVRG) algorithm was proposed by Johnson and Zhang in NIPS (2013) and has been extensively used in training neural networks. We shall rigorously prove that SVRG can be approximated by a family of stochastic differential delay equations ( SDDEs) under some conditions which include non-convex examples. It is well known that SDDEs have the effect of strong dissipations and variance reductions. Our result gives a new interpretation for SVRG. This is joint work with Peng Chen and Jianya Lu.
| 上一条： 没有了 |
| 下一条： 没有了 |
