ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2409.13272
45
3

Stochastic mirror descent for nonparametric adaptive importance sampling

20 September 2024
Pascal Bianchi
B. Delyon
Victor Priser
François Portier
ArXivPDFHTML
Abstract

This paper addresses the problem of approximating an unknown probability distribution with density fff -- which can only be evaluated up to an unknown scaling factor -- with the help of a sequential algorithm that produces at each iteration n≥1n\geq 1n≥1 an estimated density qnq_nqn​.The proposed method optimizes the Kullback-Leibler divergence using a mirror descent (MD) algorithm directly on the space of density functions, while a stochastic approximation technique helps to manage between algorithm complexity and variability. One of the key innovations of this work is the theoretical guarantee that is provided for an algorithm with a fixed MD learning rate η∈(0,1)\eta \in (0,1 )η∈(0,1). The main result is that the sequence qnq_nqn​ converges almost surely to the target density fff uniformly on compact sets. Through numerical experiments, we show that fixing the learning rate η∈(0,1)\eta \in (0,1 )η∈(0,1) significantly improves the algorithm's performance, particularly in the context of multi-modal target distributions where a small value of η\etaη allows to increase the chance of finding all modes. Additionally, we propose a particle subsampling method to enhance computational efficiency and compare our method against other approaches through numerical experiments.

View on arXiv
Comments on this paper