Speaker: Mr. Junchi Yang
From: ETH Zurich
Abstract
Machine learning applications have brought about new optimization challenges, particularly in the area of trustworthy machine learning, which requires game-theoretical formulations to seek equilibrium. Furthermore, these large-scale problems demand adaptive methods such as Adam and AdaGrad to adjust step sizes without granular knowledge of the loss functions. In this talk, I will present new algorithms that address both these quests. First, I will analyze the limitations of Stochastic Gradient Descent (SGD) and demonstrate the advantages of adaptive methods under the lack of problem information. Second, I will introduce min-max optimization problems and present a series of simple algorithms. Third, I will discuss the non-convergence issues of existing adaptive methods in non-convex min-max optimization and showcase near-optimal and tuning-free algorithms. Finally, I will outline future directions that aim to deliver efficient and robust algorithms for multi-agent systems.
For more info, please follow this link.
Read More