报告人：严明 (香港中文大学)
报告题目：Accelerated Decentralized Gradient Method Over Unbalanced Directed Graphs
摘要： We consider the decentralized optimization problem, where a network of agents aims to minimize the average of their individual smooth and convex objective functions through peer-to-peer communication in a directed graph. To tackle this problem, we propose two accelerated gradient tracking methods, namely APD and APD-SC, for non-strongly convex and strongly convex objective functions, respectively. We show that APD and APD-SC converge at the rates O(1/k^2) and O((1-C\sqrt{\mu/L})^k), respectively, up to constant factors depending only on the mixing matrix. APD and APD-SC are the first decentralized methods over unbalanced directed graphs that achieve the same provable acceleration as centralized methods.
