paper-with-me

Papers

Query lower bounds for log-concave sampling

2023-04-05 · Sinho Chewi, Jaume de Dios Pont, Jerry Li, Chen Lu, Shyam Narayanan

Log-concave sampling has witnessed remarkable algorithmic advances in recent years, but the corresponding problem of proving lower bounds for this task has remained elusive, with lower bounds previously known only in dimension one. In this work, we establish the following query lower bounds: (1) sampling from strongly log-concave and log-smooth distributions in dimension $d\ge 2$ requires $\Omega(\log \kappa)$ queries, which is sharp in any constant dimension, and (2) sampling from Gaussians in dimension $d$ (hence also from general log-concave and log-smooth distributions in dimension $d$) requires $\widetilde \Omega(\min(\sqrt\kappa \log d, d))$ queries, which is nearly sharp for the class of Gaussians. Here $\kappa$ denotes the condition number of the target distribution. Our proofs rely upon (1) a multiscale construction inspired by work on the Kakeya conjecture in geometric measure theory, and (2) a novel reduction that demonstrates that block Krylov algorithms are optimal for this problem, as well as connections to lower bound techniques based on Wishart matrices developed in the matrix-vector query literature.

📄 PDF Abstract BibTeX arXiv:2304.02599

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

The query complexity of sampling from strongly log-concave distributions in one dimension

2021-05-29 · Sinho Chewi, Patrik Gerber, Chen Lu, Thibaut Le Gouic 외

We establish the first tight lower bound of $\Omega(\log\log\kappa)$ on the query complexity of sampling from the class of strongly log-concave and log-smooth distributions with condition number $\kappa$ in one dimension…

Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds

2025-06-09 · Rishikesh Srinivasan, Dheeraj Nagaraj

We study the problem of sampling from strongly log-concave distributions over $\mathbb{R}^d$ using the Poisson midpoint discretization (a variant of the randomized midpoint method) for overdamped/underdamped Langevin dyn…

Fisher information lower bounds for sampling

2022-10-05 · Sinho Chewi, Patrik Gerber, Holden Lee, Chen Lu

We prove two lower bounds for the complexity of non-log-concave sampling within the framework of Balasubramanian et al. (2022), who introduced the use of Fisher information (FI) bounds as a notion of approximate first-or…

On the Optimal Bounds for Noisy Computing

2023-06-21 · Banghua Zhu, Ziao Wang, Nadim Ghaddar, Jiantao Jiao 외

We revisit the problem of computing with noisy information considered in Feige et al. 1994, which includes computing the OR function from noisy queries, and computing the MAX, SEARCH and SORT functions from noisy pairwis…

Quantum Algorithms for Sampling Log-Concave Distributions and Estimating Normalizing Constants

2022-10-12 · Andrew M. Childs, Tongyang Li, Jin-Peng Liu, Chunhao Wang 외

Given a convex function $f\colon\mathbb{R}^{d}\to\mathbb{R}$, the problem of sampling from a distribution $\propto e^{-f(x)}$ is called log-concave sampling. This task has wide applications in machine learning, physics, …