Statistical Estimation of the Poincar{é} constant and Application to Sampling Multimodal Distributions

Abstract

Poincar{é} inequalities are ubiquitous in probability and analysis and have various applications in statistics (concentration of measure, rate of convergence of Markov chains). The Poincar{é} constant, for which the inequality is tight, is related to the typical convergence rate of diffusions to their equilibrium measure. In this paper, we show both theoretically and experimentally that, given sufficiently many samples of a measure, we can estimate its Poincar{é} constant. As a by-product of the estimation of the Poincar{é} constant, we derive an algorithm that captures a low dimensional representation of the data by finding directions which are difficult to sample. These directions are of crucial importance for sampling or in fields like molecular dynamics, where they are called reaction coordinates. Their knowledge can leverage, with a simple conditioning step, computational bottlenecks by using importance sampling techniques.

References in corpus (5)

• Manopt, a Matlab toolbox for optimization on manifolds
• Generalization Properties of Learning with Random Features
• Non-convex learning via Stochastic Gradient Langevin Dynamics: a nonasymptotic analysis
• Accelerated dynamics: Mathematical foundations and algorithmic improvements
• An idea on proving weighted Sobolev embeddings

Cited by in corpus (4)

• Estimating the Mixing Time of Ergodic Markov Chains
• KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support
• Penalized Langevin dynamics with vanishing penalty for smooth and log-concave targets
• Overcoming the curse of dimensionality with Laplacian regularization in semi-supervised learning