Markov Chain Block Coordinate Descent

by   Tao Sun, et al.
Rensselaer Polytechnic Institute
NetEase, Inc

The method of block coordinate gradient descent (BCD) has been a powerful method for large-scale optimization. This paper considers the BCD method that successively updates a series of blocks selected according to a Markov chain. This kind of block selection is neither i.i.d. random nor cyclic. On the other hand, it is a natural choice for some applications in distributed optimization and Markov decision process, where i.i.d. random and cyclic selections are either infeasible or very expensive. By applying mixing-time properties of a Markov chain, we prove convergence of Markov chain BCD for minimizing Lipschitz differentiable functions, which can be nonconvex. When the functions are convex and strongly convex, we establish both sublinear and linear convergence rates, respectively. We also present a method of Markov chain inertial BCD. Finally, we discuss potential applications.


page 1

page 2

page 3

page 4


On Markov Chain Gradient Descent

Stochastic gradient methods are the workhorse (algorithms) of large-scal...

Experimental Study of a Parallel Iterative Solver for Markov Chain Modeling

This paper presents the results of a preliminary experimental investigat...

Decentralized Markov Chain Gradient Descent

Decentralized stochastic gradient method emerges as a promising solution...

Stochastic Gradient Descent under Markovian Sampling Schemes

We study a variation of vanilla stochastic gradient descent where the op...

Markov Chain Score Ascent: A Unifying Framework of Variational Inference with Markovian Gradients

Minimizing the inclusive Kullback-Leibler (KL) divergence with stochasti...

Conditional Markov Chain Search for the Generalised Travelling Salesman Problem for Warehouse Order Picking

The Generalised Travelling Salesman Problem (GTSP) is a well-known probl...

Active and Passive Portfolio Management with Latent Factors

We address a portfolio selection problem that combines active (outperfor...

Please sign up or login with your details

Forgot password? Click here to reset