English
Related papers

Related papers: Estimating Normalizing Constants for Log-Concave D…

200 papers

We study the problem of sampling from a distribution $\mu$ with density $\propto e^{-V}$ for some potential function $V:\mathbb R^d\to \mathbb R$ with query access to $V$ and $\nabla V$. We start with the following standard assumptions: (1)…

Data Structures and Algorithms · Computer Science 2026-02-10 Yuchen He , Zhehan Lei , Jianan Shao , Chihao Zhang

In this paper, we study a method to sample from a target distribution $\pi$ over $\mathbb{R}^d$ having a positive density with respect to the Lebesgue measure, known up to a normalisation factor. This method is based on the Euler…

Statistics Theory · Mathematics 2016-12-20 Alain Durmus , Eric Moulines

The problem of sampling according to the probability distribution minimizing a given free energy, using interacting particles unadjusted kinetic Langevin Monte Carlo, is addressed. In this setting, three sources of error arise, related to…

Probability · Mathematics 2024-12-05 Pierre Monmarché , Katharina Schuh

We prove lower bounds on the complexity of finding $\epsilon$-stationary points (points $x$ such that $\|\nabla f(x)\| \le \epsilon$) of smooth, high-dimensional, and potentially non-convex functions $f$. We consider oracle-based complexity…

Optimization and Control · Mathematics 2019-08-16 Yair Carmon , John C. Duchi , Oliver Hinder , Aaron Sidford

We introduce a framework for proving lower bounds on computational problems over distributions against algorithms that can be implemented using access to a statistical query oracle. For such algorithms, access to the input distribution is…

Computational Complexity · Computer Science 2016-08-16 Vitaly Feldman , Elena Grigorescu , Lev Reyzin , Santosh Vempala , Ying Xiao

We study the problem of sampling from a $d$-dimensional distribution with density $p(x)\propto e^{-f(x)}$, which does not necessarily satisfy good isoperimetric conditions. Specifically, we show that for any $L,M$ satisfying $LM\ge d\ge 5$,…

Data Structures and Algorithms · Computer Science 2025-06-04 Yuchen He , Chihao Zhang

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…

Statistics Theory · Mathematics 2023-10-31 Sinho Chewi , Jaume de Dios Pont , Jerry Li , Chen Lu , Shyam Narayanan

Probability distributions supported on the simplex enjoy a wide range of applications across statistics and machine learning. Recently, a novel family of such distributions has been discovered: the continuous categorical. This family enjoys…

Minimizing a convex, quadratic objective of the form $f_{\mathbf{A},\mathbf{b}}(x) := \frac{1}{2}x^\top \mathbf{A} x - \langle \mathbf{b}, x \rangle$ for $\mathbf{A} \succ 0 $ is a fundamental problem in machine learning and optimization.…

Machine Learning · Computer Science 2019-04-17 Max Simchowitz

We study the problem of sampling from a distribution $\target$ using the Langevin Monte Carlo algorithm and provide rate of convergences for this algorithm in terms of Wasserstein distance of order $2$. Our result holds as long as the…

Computation · Statistics 2016-07-04 Thomas Bonis

Calculation of the log-normalizer is a major computational obstacle in applications of log-linear models with large output spaces. The problem of fast normalizer computation has therefore attracted significant attention in the theoretical…

Machine Learning · Statistics 2015-06-19 Jacob Andreas , Maxim Rabinovich , Dan Klein , Michael I. Jordan

Consider a family of distributions $\{\pi_{\beta}\}$ where $X\sim\pi_{\beta}$ means that $\mathbb{P}(X=x)=\exp(-\beta H(x))/Z(\beta)$. Here $Z(\beta)$ is the proper normalizing constant, equal to $\sum_x\exp(-\beta H(x))$. Then…

Probability · Mathematics 2015-03-19 Mark Huber

We study the problem of sampling from a probability distribution $\pi$ on $\rset^d$ which has a density \wrt\ the Lebesgue measure known up to a normalization factor $x \mapsto \rme^{-U(x)} / \int_{\rset^d} \rme^{-U(y)} \rmd y$. We analyze…

Statistics Theory · Mathematics 2019-09-17 M. Barkhagen , N. H. Chau , É. Moulines , M. Rásonyi , S. Sabanis , Y. Zhang

Recent research has developed several Monte Carlo methods for estimating the normalization constant (partition function) based on the idea of annealing. This means sampling successively from a path of distributions that interpolate between…

Machine Learning · Statistics 2023-10-10 Omar Chehab , Aapo Hyvarinen , Andrej Risteski

This is an up-to-date introduction to, and overview of, marginal likelihood computation for model selection and hypothesis testing. Computing normalizing constants of probability models (or ratio of constants) is a fundamental issue in many…

Computation · Statistics 2023-02-13 Fernando Llorente , Luca Martino , David Delgado , Javier Lopez-Santiago

In this paper, we provide new insights on the Unadjusted Langevin Algorithm. We show that this method can be formulated as a first order optimization algorithm of an objective functional defined on the Wasserstein space of order $2$. Using…

Computation · Statistics 2018-03-30 Alain Durmus , Szymon Majewski , Błażej Miasojedow

The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and have the advantage of being inherently parallelizable. However, the standard…

Machine Learning · Statistics 2016-08-16 Marco Fraccaro , Ulrich Paquet , Ole Winther

In this paper, we study the problem of sampling from log-concave distributions supported on convex, compact sets, with a particular focus on the randomized midpoint discretization of both vanilla and kinetic Langevin diffusions in this…

Machine Learning · Statistics 2025-05-27 Yifeng Yu , Lu Yu

Langevin Monte Carlo (LMC) is an iterative algorithm used to generate samples from a distribution that is known only up to a normalizing constant. The nonasymptotic dependence of its mixing time on the dimension and target accuracy is…

Machine Learning · Statistics 2020-02-26 Niladri S. Chatterji , Jelena Diakonikolas , Michael I. Jordan , Peter L. Bartlett

We study and develop multilevel methods for the numerical approximation of a log-concave probability $\pi$ on $\mathbb{R}^d$, based on (over-damped) Langevin diffusion. In the continuity of \cite{art:egeapanloup2021multilevel} concentrated…

Numerical Analysis · Mathematics 2023-01-24 Maxime Egéa