English

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

Statistics Theory 2024-05-28 v1 Machine Learning Statistics Theory

Abstract

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/ε))O(\log(1/\varepsilon)) versus Ω(poly(1/ε))\Omega(\text{poly}(1/\varepsilon)) iterations to output a sample which is ε\varepsilon-close to the target in χ2\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.

Keywords

Cite

@article{arxiv.2405.16736,
  title  = {A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers},
  author = {Ye He and Alireza Mousavi-Hosseini and Krishnakumar Balasubramanian and Murat A. Erdogdu},
  journal= {arXiv preprint arXiv:2405.16736},
  year   = {2024}
}
R2 v1 2026-06-28T16:41:08.742Z