Variance reduction for Random Coordinate Descent-Langevin Monte Carlo

Abstract

Sampling from a log-concave distribution function is one core problem that has wide applications in Bayesian statistics and machine learning. While most gradient free methods have slow convergence rate, the Langevin Monte Carlo (LMC) that provides fast convergence requires the computation of gradients. In practice one uses finite-differencing approximations as surrogates, and the method is expensive in high-dimensions. A natural strategy to reduce computational cost in each iteration is to utilize random gradient approximations, such as random coordinate descent (RCD) or simultaneous perturbation stochastic approximation (SPSA). We show by a counter-example that blindly applying RCD does not achieve the goal in the most general setting. The high variance induced by the randomness means a larger number of iterations are needed, and this balances out the saving in each iteration. We then introduce a new variance reduction approach, termed Randomized Coordinates Averaging Descent (RCAD), and incorporate it with both overdamped and underdamped LMC. The methods are termed RCAD-O-LMC and RCAD-U-LMC respectively. The methods still sit in the random gradient approximation framework, and thus the computational cost in each iteration is low. However, by employing RCAD, the variance is reduced, so the methods converge within the same number of iterations as the classical overdamped and underdamped LMC. This leads to a computational saving overall.

References in corpus (11)

• General state space Markov chains and MCMC algorithms
• Stochastic Gradient Hamiltonian Monte Carlo
• The Ensemble Kalman Filter for Inverse Problems
• User-friendly guarantees for the Langevin Monte Carlo with inaccurate gradient
• Log-concave sampling: Metropolis-Hastings algorithms are fast
• High-Order Langevin Diffusion Yields an Accelerated MCMC Algorithm
• Ensemble Kalman Sampler: mean-field limit and convergence analysis
• A mixture representation of πwith applications in Markov chain Monte Carlo and perfect sampling
• Global Convergence of Stochastic Gradient Hamiltonian Monte Carlo for Non-Convex Stochastic Optimization: Non-Asymptotic Performance Bounds and Momentum-Based Acceleration
• Gradient-free Hamiltonian Monte Carlo with Efficient Kernel Exponential Families
• Dimensionally Tight Bounds for Second-Order Hamiltonian Monte Carlo