报告题目：From differential equation solvers to accelerated first-order methods for convex optimization
邀请人：黄学海
报告人：陈龙 教授 美国加州大学尔湾分校
时间：2019年7月18日（周四）14:30-15:30
地点：红瓦楼723
摘要：Convergence analysis of accelerated first-order methods for convex optimization problems are presented from the point of view of ordinary differential equation (ODE) solvers. Two resolution ODEs are derived for accelerated gradient methods. Numerical discretizations for these resolution ODEs are considered and its convergence analyses are established via tailored Lyapunov functions. The ODE solvers approach can not only cover existing methods, such as Nesterov's accelerated gradient method and FISTA, but also produce a large class of new algorithms that possesses optimal convergence rates. This is a joint work with Hao Luo from Sichuan University