English
Related papers

Related papers: Online Sampling from Log-Concave Distributions

200 papers

In this paper, we propose a novel class of Piecewise Deterministic Markov Processes (PDMPs) that are designed to sample from probability distributions $\pi$ supported on a convex set $\mathcal{M}$. This class of PDMPs adapts the concept of…

Computation · Statistics 2026-05-01 Joël Tatang Demano , Paul Dobson , Konstantinos Zygalakis

We study parameter inference in large-scale latent variable models. We first propose an unified treatment of online inference for latent variable models from a non-canonical exponential family, and draw explicit links between several…

Machine Learning · Computer Science 2018-02-01 Christophe Dupuy , Francis Bach

Spaces of convex and concave functions appear naturally in theory and applications. For example, convex regression and log-concave density estimation are important topics in nonparametric statistics. In stochastic portfolio theory, concave…

Probability · Mathematics 2021-05-25 Peter Baxendale , Ting-Kam Leonard Wong

Matrix completion, where we wish to recover a low rank matrix by observing a few entries from it, is a widely studied problem in both theory and practice with wide applications. Most of the provable algorithms so far on this problem have…

Machine Learning · Computer Science 2016-05-27 Chi Jin , Sham M. Kakade , Praneeth Netrapalli

We provide new results for noise-tolerant and sample-efficient learning algorithms under $s$-concave distributions. The new class of $s$-concave distributions is a broad and natural generalization of log-concavity, and includes many…

Machine Learning · Statistics 2018-01-30 Maria-Florina Balcan , Hongyang Zhang

Constrained sampling is an important and challenging task in computational statistics, concerned with generating samples from a distribution under certain constraints. There are numerous types of algorithm aimed at this task, ranging from…

Methodology · Statistics 2026-04-01 Neil K. Chada , Lu Yu

In this paper, we examine the problem of sampling from log-concave distributions with (possibly) superlinear gradient growth under kinetic (underdamped) Langevin algorithms. Using a carefully tailored taming scheme, we propose two novel…

Probability · Mathematics 2025-12-10 Iosif Lytras , Panayotis Mertikopoulos

A new (unadjusted) Langevin Monte Carlo (LMC) algorithm with improved rates in total variation and in Wasserstein distance is presented. All these are obtained in the context of sampling from a target distribution $\pi$ that has a density…

Statistics Theory · Mathematics 2019-10-18 Sotirios Sabanis , Ying Zhang

We study the Stochastic Gradient Langevin Dynamics (SGLD) algorithm for non-convex optimization. The algorithm performs stochastic gradient descent, where in each step it injects appropriately scaled Gaussian noise to the update. We analyze…

Machine Learning · Computer Science 2018-04-10 Yuchen Zhang , Percy Liang , Moses Charikar

Dependency networks (Heckerman et al., 2000) are potential probabilistic graphical models for systems comprising a large number of variables. Like Bayesian networks, the structure of a dependency network is represented by a directed graph,…

Machine Learning · Computer Science 2021-07-05 Kazuya Takabatake , Shotaro Akaho

Decentralized optimization strategies are helpful for various applications, from networked estimation to distributed machine learning. This paper studies finite-sum minimization problems described over a network of nodes and proposes a…

Systems and Control · Electrical Eng. & Systems 2024-08-06 Mohammadreza Doostmohammadian , Zulfiya R. Gabidullina , Hamid R. Rabiee

This work establishes a novel link between the problem of PAC-learning high-dimensional graphical models and the task of (efficient) counting and sampling of graph structures, using an online learning framework. We observe that if we apply…

Machine Learning · Computer Science 2025-11-14 Arnab Bhattacharyya , Sutanu Gayen , Philips George John , Sayantan Sen , N. V. Vinodchandran

Conventional machine learning applications typically assume that data samples are independently and identically distributed (i.i.d.). However, practical scenarios often involve a data-generating process that produces highly dependent data…

Machine Learning · Computer Science 2022-04-04 Shaocong Ma , Ziyi Chen , Yi Zhou , Kaiyi Ji , Yingbin Liang

To maintain the accuracy of supervised learning models in the presence of evolving data streams, we provide temporally-biased sampling schemes that weight recent data most heavily, with inclusion probabilities for a given data item decaying…

Databases · Computer Science 2018-01-31 Brian Hentschel , Peter J. Haas , Yuanyuan Tian

To maintain the accuracy of supervised learning models in the presence of evolving data streams, we provide temporally-biased sampling schemes that weight recent data most heavily, with inclusion probabilities for a given data item decaying…

Databases · Computer Science 2019-06-14 Brian Hentschel , Peter J. Haas , Yuanyuan Tian

The Langevin Markov chain algorithms are widely deployed methods to sample from distributions in challenging high-dimensional and non-convex statistics and machine learning applications. Despite this, current bounds for the Langevin…

Data Structures and Algorithms · Computer Science 2019-04-10 Oren Mangoubi , Nisheeth K. Vishnoi

We propose and analyze a class of adaptive sampling algorithms for multimodal distributions on a bounded domain, which share a structural resemblance to the classic overdamped Langevin dynamics. We first demonstrate that this class of…

Machine Learning · Computer Science 2024-11-26 Björn Engquist , Kui Ren , Yunan Yang

We investigate the complexity of covariance matrix estimation for Gibbs distributions based on dependent samples from a Markov chain. We show that when $\pi$ satisfies a Poincar\'e inequality and the chain possesses a spectral gap, we can…

Statistics Theory · Mathematics 2024-10-23 Yunbum Kook , Matthew S. Zhang

This paper studies a class of distributed optimization problems with coupled equality constraints in networked systems. Many existing distributed algorithms rely on solving local subproblems via the $\operatorname{argmin}$ operator in each…

Optimization and Control · Mathematics 2025-11-26 Chenyang Qiu , Zongli Lin

To learn (statistical) dependencies among random variables requires exponentially large sample size in the number of observed random variables if any arbitrary joint probability distribution can occur. We consider the case that sparse data…

Machine Learning · Computer Science 2007-05-23 Dominik Janzing , Daniel Herrmann