English
Related papers

Related papers: Zeroth-order Logconcave Sampling

200 papers

In this paper, a new semi-discrete version of the Carleman estimate-based convexification globally convergent numerical method is developed. It is used for the delivery of the starting point for the training procedure of deep learning. An…

Analysis of PDEs · Mathematics 2026-02-23 Michael V. Klibanov , Kirill V. Golubnichiy , Benjamin Jiang

We show that high-accuracy guarantees for log-concave sampling -- that is, iteration and query complexities which scale as $\mathrm{poly}\log(1/\delta)$, where $\delta$ is the desired target accuracy -- are achievable using stochastic…

Statistics Theory · Mathematics 2026-05-18 Fan Chen , Sinho Chewi , Constantinos Daskalakis , Alexander Rakhlin

Adaptive sampling algorithms are modern and efficient methods that dynamically adjust the sample size throughout the optimization process. However, they may encounter difficulties in risk-averse settings, particularly due to the challenge…

Optimization and Control · Mathematics 2025-02-17 Sandra Pieraccini , Tommaso Vanzan

We consider the inverse problem of determining the geometry of penetrable objects from scattering data generated by one incident wave at a fixed frequency. We first study an orthogonality sampling type method which is fast, simple to…

Numerical Analysis · Mathematics 2022-07-21 Thu Le , Dinh-Liem Nguyen , Vu Nguyen , Trung Truong

We consider a general supervised learning problem with strongly convex and Lipschitz loss and study the problem of model selection aggregation. In particular, given a finite dictionary functions (learners) together with the prior, we…

Statistics Theory · Mathematics 2014-02-28 Guillaume Lecué , Philippe Rigollet

Estimating the normalizing constant of an unnormalized probability distribution has important applications in computer science, statistical physics, machine learning, and statistics. In this work, we consider the problem of estimating the…

Data Structures and Algorithms · Computer Science 2020-06-25 Rong Ge , Holden Lee , Jianfeng Lu

We study the multi-terminal remote estimation problem under a rate constraint, in which the goal of the encoder is to help each decoder estimate a function over a certain distribution -- while the distribution is known only to the encoder,…

Information Theory · Computer Science 2025-05-13 Maximilian Egger , Rawad Bitar , Antonia Wachter-Zeh , Nir Weinberger , Deniz Gündüz

A conditional sampling oracle for a probability distribution D returns samples from the conditional distribution of D restricted to a specified subset of the domain. A recent line of work (Chakraborty et al. 2013 and Cannone et al. 2014)…

Data Structures and Algorithms · Computer Science 2016-08-18 Themistoklis Gouleakis , Christos Tzamos , Manolis Zampetakis

Risk minimization for nonsmooth nonconvex problems naturally leads to first-order sampling or, by an abuse of terminology, to stochastic subgradient descent. We establish the convergence of this method in the path-differentiable case and…

Optimization and Control · Mathematics 2024-07-24 Jérôme Bolte , Tam Le , Edouard Pauwels

Mean field variational inference (VI) is the problem of finding the closest product (factorized) measure, in the sense of relative entropy, to a given high-dimensional probability measure $\rho$. The well known Coordinate Ascent Variational…

Machine Learning · Statistics 2024-04-16 Manuel Arnese , Daniel Lacker

Sampling is a fundamental algorithmic task in wide-ranging applications across multiple disciplines such as scientific computing, statistics and machine learning. In this paper, an efficient stochastic Runge-Kutta scheme is proposed to…

Statistics Theory · Mathematics 2026-05-27 Haotian Lin , Xiaojie Wang , Xiaoyan Zhang

Augmenting algorithms with learned predictions is a promising approach for going beyond worst-case bounds. Dinitz, Im, Lavastida, Moseley, and Vassilvitskii~(2021) have demonstrated that a warm start with learned dual solutions can improve…

Machine Learning · Computer Science 2022-05-23 Shinsaku Sakaue , Taihei Oki

Two commonly arising computational tasks in Bayesian learning are Optimization (Maximum A Posteriori estimation) and Sampling (from the posterior distribution). In the convex case these two problems are efficiently reducible to each other.…

Machine Learning · Computer Science 2019-11-07 Kunal Talwar

There has been a recent surge of powerful tools to show rapid mixing of Markov chains, via functional inequalities such as Poincar\'e inequalities. In many situations, Markov chains fail to mix rapidly from a worst-case initialization, yet…

Probability · Mathematics 2024-11-25 Brice Huang , Sidhanth Mohanty , Amit Rajaraman , David X. Wu

We study the Riemannian Langevin Algorithm for the problem of sampling from a distribution with density $\nu$ with respect to the natural measure on a manifold with metric $g$. We assume that the target density satisfies a log-Sobolev…

Machine Learning · Computer Science 2022-04-25 Khashayar Gatmiry , Santosh S. Vempala

Given a Lipschitz or smooth convex function $\, f:K \to \mathbb{R}$ for a bounded polytope $K \subseteq \mathbb{R}^d$ defined by $m$ inequalities, we consider the problem of sampling from the log-concave distribution $\pi(\theta) \propto…

Data Structures and Algorithms · Computer Science 2022-11-16 Oren Mangoubi , Nisheeth K. Vishnoi

We study the problem of exact sampling under an exponential communication cost, specifically Campbell's average codeword length $L(t)$ of order $t$, and R\'enyi's entropy. We provide a lower bound on the Campbell cost of exact sampling that…

Information Theory · Computer Science 2026-04-03 Spencer Hill , Fady Alajaji , Tamás Linder

In 2016, Karney proposed an exact sampling algorithm for the standard normal distribution. In this paper, we study the computational complexity of this algorithm under the random deviate model. Specifically, Karney's algorithm requires the…

Data Structures and Algorithms · Computer Science 2020-08-11 Yusong Du , Baoying Fan , Baodian Wei

We provide a new convergence analysis of stochastic gradient Langevin dynamics (SGLD) for sampling from a class of distributions that can be non-log-concave. At the core of our approach is a novel conductance analysis of SGLD using an…

Machine Learning · Computer Science 2021-02-24 Difan Zou , Pan Xu , Quanquan Gu

In Bayesian statistics, exploring high-dimensional multimodal posterior distributions poses major challenges for existing MCMC approaches. This paper introduces the Annealed Leap-Point Sampler (ALPS), which augments the target distribution…

Methodology · Statistics 2026-02-10 Nicholas G. Tawn , Matthew T. Moores , Hugo Queniat , Gareth O. Roberts