Non-Ergodic Convergence Analysis of Heavy-Ball Algorithms

In this paper, we revisit the convergence of the Heavy-ball method, and present improved convergence complexity results in the convex setting. We provide the first non-ergodic O(1/k) rate result of the Heavy-ball algorithm with constant step size for coercive objective functions. For objective functions satisfying a relaxed strongly convex condition, the linear convergence is established under weaker assumptions on the step size and inertial parameter than made in the existing literature. We extend our results to multi-block version of the algorithm with both the cyclic and stochastic update rules. In addition, our results can also be extended to decentralized optimization, where the ergodic analysis is not applicable.

Stabilization for Networked Control Systems with Limited Communication

This paper studies the stabilization problems of networked control systems (NCSs) with dynamical quantizers. A new model is proposed that takes into consideration the effect of the network induced delay, the quantization levels, and based on this model, dynamical quantization scheme is introduced. The relationship between the delay bound，the quantization range and stability is given by using Lyapunov stability theory and linear matrix inequalities (LMIs) approach, and convex condition of the stabilization controller is presented. A simulation example shows the effectiveness of the proposed method.