paper-with-me

Papers

A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers

2024-05-27 · Ye He, Alireza Mousavi-Hosseini, Krishnakumar Balasubramanian, Murat A. Erdogdu

We study the complexity of heavy-tailed sampling and present a separation result in terms of obtaining high-accuracy versus low-accuracy guarantees i.e., samplers that require only $O(\log(1/\varepsilon))$ versus $\Omega(\text{poly}(1/\varepsilon))$ iterations to output a sample which is $\varepsilon$-close to the target in $\chi^2$-divergence. Our results are presented for proximal samplers that are based on Gaussian versus stable oracles. We show that proximal samplers based on the Gaussian oracle have a fundamental barrier in that they necessarily achieve only low-accuracy guarantees when sampling from a class of heavy-tailed targets. In contrast, proximal samplers based on the stable oracle exhibit high-accuracy guarantees, thereby overcoming the aforementioned limitation. We also prove lower bounds for samplers under the stable oracle and show that our upper bounds cannot be fundamentally improved.

📄 PDF Abstract BibTeX arXiv:2405.16736

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Robust Kalman Filters Based on the Sub-Gaussian $α$-stable Distribution

2023-05-13 · Pengcheng Hao, Oktay Karakuş, Alin Achim

Motivated by filtering tasks under a linear system with non-Gaussian heavy-tailed noise, various robust Kalman filters (RKFs) based on different heavy-tailed distributions have been proposed. Although the sub-Gaussian $\…

Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation

2022-05-11 · Mathieu Fontaine, Kouhei Sekiguchi, Aditya Nugraha, Yoshiaki Bando 외

This paper describes heavy-tailed extensions of a state-of-the-art versatile blind source separation method called fast multichannel nonnegative matrix factorization (FastMNMF) from a unified point of view. The common wa…

blind source separationSpeech Enhancement

Denoising Lévy Probabilistic Models

2024-07-26 · Dario Shariatian, Umut Simsekli, Alain Durmus

Investigating noise distribution beyond Gaussian in diffusion generative models is an open problem. The Gaussian case has seen success experimentally and theoretically, fitting a unified SDE framework for score-based and…

Denoising

Non-Asymptotic Analysis of Fractional Langevin Monte Carlo for Non-Convex Optimization

2019-01-22 · Thanh Huy Nguyen, Umut Şimşekli, Gaël Richard

Recent studies on diffusion-based sampling methods have shown that Langevin Monte Carlo (LMC) algorithms can be beneficial for non-convex optimization, and rigorous theoretical guarantees have been proven for both asympt…

q-exponential family for policy optimization

2024-08-14 · Lingwei Zhu, Haseeb Shah, Han Wang, Yukie Nagai 외

Policy optimization methods benefit from a simple and tractable policy parametrization, usually the Gaussian for continuous action spaces. In this paper, we consider a broader policy family that remains tractable: the $q…