Sampling as Bandits: Evaluation-Efficient Design for Black-Box Densities
- URL: http://arxiv.org/abs/2509.01437v1
- Date: Mon, 01 Sep 2025 12:47:32 GMT
- Title: Sampling as Bandits: Evaluation-Efficient Design for Black-Box Densities
- Authors: Takuo Matsubara, Andrew Duncan, Simon Cotter, Konstantinos Zygalakis,
- Abstract summary: bandit importance sampling (BIS) is a new class of importance sampling methods designed for settings where the target density is expensive to evaluate.<n>BIS directly designs the samples through a sequential strategy that combines space-filling designs with multi-armed bandits.
- Score: 5.029813736862755
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: We introduce bandit importance sampling (BIS), a new class of importance sampling methods designed for settings where the target density is expensive to evaluate. In contrast to adaptive importance sampling, which optimises a proposal distribution, BIS directly designs the samples through a sequential strategy that combines space-filling designs with multi-armed bandits. Our method leverages Gaussian process surrogates to guide sample selection, enabling efficient exploration of the parameter space with minimal target evaluations. We establish theoretical guarantees on convergence and demonstrate the effectiveness of the method across a broad range of sampling tasks. BIS delivers accurate approximations with fewer target evaluations, outperforming competing approaches across multimodal, heavy-tailed distributions, and real-world applications to Bayesian inference of computationally expensive models.
Related papers
- Learnable Chernoff Baselines for Inference-Time Alignment [64.81256817158851]
We introduce Learnable Chernoff Baselines as a method for efficiently and approximately sampling from exponentially tilted kernels.<n>We establish total-variation guarantees to the ideal aligned model, and demonstrate in both continuous and discrete diffusion settings that LCB sampling closely matches ideal rejection sampling.
arXiv Detail & Related papers (2026-02-08T00:09:40Z) - G$^2$RPO: Granular GRPO for Precise Reward in Flow Models [74.21206048155669]
We propose a novel Granular-GRPO (G$2$RPO) framework that achieves precise and comprehensive reward assessments of sampling directions.<n>We introduce a Multi-Granularity Advantage Integration module that aggregates advantages computed at multiple diffusion scales.<n>Our G$2$RPO significantly outperforms existing flow-based GRPO baselines.
arXiv Detail & Related papers (2025-10-02T12:57:12Z) - Optimality in importance sampling: a gentle survey [50.79602839359522]
The performance of Monte Carlo sampling methods relies on the crucial choice of a proposal density.<n>This work is an exhaustive review around the concept of optimality in importance sampling.
arXiv Detail & Related papers (2025-02-11T09:23:26Z) - Enhanced Importance Sampling through Latent Space Exploration in Normalizing Flows [69.8873421870522]
importance sampling is a rare event simulation technique used in Monte Carlo simulations.<n>We propose a method for more efficient sampling by updating the proposal distribution in the latent space of a normalizing flow.
arXiv Detail & Related papers (2025-01-06T21:18:02Z) - Learned Reference-based Diffusion Sampling for multi-modal distributions [2.1383136715042417]
We introduce Learned Reference-based Diffusion Sampler (LRDS), a methodology specifically designed to leverage prior knowledge on the location of the target modes.<n>LRDS proceeds in two steps by learning a reference diffusion model on samples located in high-density space regions.<n>We experimentally demonstrate that LRDS best exploits prior knowledge on the target distribution compared to competing algorithms on a variety of challenging distributions.
arXiv Detail & Related papers (2024-10-25T10:23:34Z) - TS-RSR: A provably efficient approach for batch Bayesian Optimization [4.622871908358325]
This paper presents a new approach for batch Bayesian Optimization (BO) called Thompson Sampling-Regret to Sigma Ratio directed sampling.<n>Our sampling objective is able to coordinate the actions chosen in each batch in a way that minimizes redundancy between points.<n>We demonstrate that our method attains state-of-the-art performance on a range of challenging synthetic and realistic test functions.
arXiv Detail & Related papers (2024-03-07T18:58:26Z) - Distributed Markov Chain Monte Carlo Sampling based on the Alternating
Direction Method of Multipliers [143.6249073384419]
In this paper, we propose a distributed sampling scheme based on the alternating direction method of multipliers.
We provide both theoretical guarantees of our algorithm's convergence and experimental evidence of its superiority to the state-of-the-art.
In simulation, we deploy our algorithm on linear and logistic regression tasks and illustrate its fast convergence compared to existing gradient-based methods.
arXiv Detail & Related papers (2024-01-29T02:08:40Z) - Optimal Budgeted Rejection Sampling for Generative Models [54.050498411883495]
Rejection sampling methods have been proposed to improve the performance of discriminator-based generative models.
We first propose an Optimal Budgeted Rejection Sampling scheme that is provably optimal.
Second, we propose an end-to-end method that incorporates the sampling scheme into the training procedure to further enhance the model's overall performance.
arXiv Detail & Related papers (2023-11-01T11:52:41Z) - LSB: Local Self-Balancing MCMC in Discrete Spaces [2.385916960125935]
This work considers using machine learning to adapt the proposal distribution to the target, in order to improve the sampling efficiency in the purely discrete domain.
We call the resulting sampler as the Locally Self-Balancing Sampler (LSB)
arXiv Detail & Related papers (2021-09-08T18:31:26Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.