Accelerating Langevin Monte Carlo Sampling: A Large Deviations Analysis
By: Nian Yao , Pervez Ali , Xihua Tao and more
Potential Business Impact:
Speeds up computer learning with better math.
Langevin algorithms are popular Markov chain Monte Carlo methods that are often used to solve high-dimensional large-scale sampling problems in machine learning. The most classical Langevin Monte Carlo algorithm is based on the overdamped Langevin dynamics. There are many variants of Langevin dynamics that often show superior performance in practice. In this paper, we provide a unified approach to study the acceleration of the variants of the overdamped Langevin dynamics through the lens of large deviations theory. Numerical experiments using both synthetic and real data are provided to illustrate the efficiency of these variants.
Similar Papers
Accelerating Constrained Sampling: A Large Deviations Approach
Machine Learning (Stat)
Makes computer learning faster and more accurate.
Analysis of kinetic Langevin Monte Carlo under the stochastic exponential Euler discretization from underdamped all the way to overdamped
Computation
Makes computer simulations of physics more accurate.
A Langevin sampling algorithm inspired by the Adam optimizer
Computation
Helps computers learn faster and more accurately.