math.OC

Understanding Accelerated Stochastic Gradient Descent via the Growth Condition

We study accelerated stochastic gradient descent through the lens of the growth condition. Stochastic gradient methods (SGD) with momentum, such as heavy ball (HB) and Nesterov's accelerated methods (NAM), are widely used in practice, especially for …

Natural Actor-Critic Converges Globally for Hierarchical Linear Quadratic Regulator

Multi-agent reinforcement learning has been successfully applied to a number of challenging problems. Despite these empirical successes, theoretical understanding of different algorithms is lacking, primarily due to the curse of dimensionality caused …