Global convergence of optimized adaptive importance samplers
FOUNDATIONS OF DATA SCIENCE(2024)
Abstract
We analyze the optimized adaptive importance sampler (OAIS) for performing Monte Carlo integration with general proposals. We leverage a classical result which shows that the bias and the mean-squared error (MSE) of the importance sampling scales with the chi(2)-divergence between the target and the proposal and develop a scheme which performs global optimization of chi(2)-divergence. While it is known that this quantity is convex for exponential family proposals, the case of the general proposals has been an open problem. We close this gap by utilizing the nonasymptotic bounds for stochastic gradient Langevin dynamics (SGLD) for the global optimization of chi(2)-divergence and derive nonasymptotic bounds for the MSE by leveraging recent results from non-convex optimization literature. The resulting AIS schemes have explicit theoretical guarantees that are uniform -in -time.
MoreTranslated text
Key words
Adaptive importance sampling,variance minimization,non-convex optimization
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined