English
Related papers

Related papers: Normalizing constants of log-concave densities

200 papers

Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective. Compared with samplers with unbiased stationary…

Machine Learning · Computer Science 2024-03-12 Xunpeng Huang , Hanze Dong , Difan Zou , Tong Zhang

We propose a new approach to deriving quantitative mean field approximations for any probability measure $P$ on $\mathbb{R}^n$ with density proportional to $e^{f(x)}$, for $f$ strongly concave. We bound the mean field approximation for the…

Probability · Mathematics 2022-06-06 Daniel Lacker , Sumit Mukherjee , Lane Chun Yeung

We propose a unified framework for likelihood-based regression modeling when the response variable has finite support. Our work is motivated by the fact that, in practice, observed data are discrete and bounded. The proposed methods assume…

Methodology · Statistics 2022-09-13 Karl Oskar Ekvall , Matteo Bottai

Score-based generative modeling, implemented through probability flow ODEs, has shown impressive results in numerous practical settings. However, most convergence guarantees rely on restrictive regularity assumptions on the target…

Machine Learning · Statistics 2025-10-21 Gitte Kremling , Francesco Iafrate , Mahsa Taheri , Johannes Lederer

Laplace-type results characterize the limit of sequence of measures $(\pi_\varepsilon)_{\varepsilon >0}$ with density w.r.t the Lebesgue measure $(\mathrm{d} \pi_\varepsilon / \mathrm{d} \mathrm{Leb})(x) \propto \exp[-U(x)/\varepsilon]$…

Probability · Mathematics 2026-04-29 Valentin De Bortoli , Agnès Desolneux

In this article we consider sampling from log concave distributions in Hamiltonian setting, without assuming that the objective gradient is globally Lipschitz. We propose two algorithms based on monotone polygonal (tamed) Euler schemes, to…

Probability · Mathematics 2023-01-20 Tim Johnston , Iosif Lytras , Sotirios Sabanis

A novel computational approach to log-concave density estimation is proposed. Previous approaches utilize the piecewise-affine parametrization of the density induced by the given sample set. The number of parameters as well as non-smooth…

Computation · Statistics 2019-02-21 Fabian Rathke , Christoph Schnörr

In this note, we propose a probabilistic approach to bound the (dimension-free) Lipschitz constant of the Langevin flow map on $\mathbb{R}^d$ introduced by Kim and Milman (2012). As example of application, we construct Lipschitz maps from a…

Probability · Mathematics 2025-02-04 Giovanni Conforti , Katharina Eichinger

In this paper, we consider a finite-dimensional optimization problem minimizing a continuous objective on a compact domain subject to a multi-dimensional constraint function. For the latter, we assume the availability of a global Lipschitz…

Optimization and Control · Mathematics 2026-02-11 Adrian Göß , Alexander Martin , Sebastian Pokutta , Kartikey Sharma

We study regression of $1$-Lipschitz functions under a log-concave measure $\mu$ on $\mathbb{R}^d$. We focus on the high-dimensional regime where the sample size $n$ is subexponential in $d$, in which distribution-free estimators are…

Probability · Mathematics 2025-09-15 Pierre Bizeul , Boaz Klartag

The estimation of a log-concave density on $\mathbb{R}^d$ represents a central problem in the area of nonparametric inference under shape constraints. In this paper, we study the performance of log-concave density estimators with respect to…

Statistics Theory · Mathematics 2015-09-29 Arlene K. H. Kim , Richard J. Samworth

Bayesian inference requires approximation methods to become computable, but for most of them it is impossible to quantify how close the approximation is to the true posterior. In this work, we present a theorem upper-bounding the KL…

Machine Learning · Statistics 2017-11-27 Guillaume P. Dehaene

For renormalizable theories with a single coupling constant regularized by higher derivatives we investigate the coefficients at powers of logarithms present in the renormalization constants assuming that divergences are removed by minimal…

High Energy Physics - Theory · Physics 2022-10-14 Nikolai Meshcheriakov , Victoria Shatalova , Konstantin Stepanyantz

We introduce a theoretical framework for sampling from unnormalized densities based on a smoothing scheme that uses an isotropic Gaussian kernel with a single fixed noise scale. We prove one can decompose sampling from a density (minimal…

Machine Learning · Statistics 2023-10-02 Saeed Saremi , Ji Won Park , Francis Bach

It is well-known that measures whose density is the form $e^{-V}$ where $V$ is a uniformly convex potential on $\RR^n$ attain strong concentration properties. In search of a notion of log-concavity on the discrete hypercube, we consider…

Probability · Mathematics 2020-07-28 Ronen Eldan , Omer Shamir

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

Normalizing flows are a widely used class of latent-variable generative models with a tractable likelihood. Affine-coupling (Dinh et al, 2014-16) models are a particularly common type of normalizing flows, for which the Jacobian of the…

Machine Learning · Computer Science 2021-07-08 Holden Lee , Chirag Pabbaraju , Anish Sevekari , Andrej Risteski

Langevin diffusions are rapidly convergent under appropriate functional inequality assumptions. Hence, it is natural to expect that with additional smoothness conditions to handle the discretization errors, their discretizations like the…

Statistics Theory · Mathematics 2023-07-21 Alireza Mousavi-Hosseini , Tyler Farghly , Ye He , Krishnakumar Balasubramanian , Murat A. Erdogdu

Consider reconstructing a signal $x$ by minimizing a weighted sum of a convex differentiable negative log-likelihood (NLL) (data-fidelity) term and a convex regularization term that imposes a convex-set constraint on $x$ and enforces its…

Computation · Statistics 2017-02-28 Renliang Gu , Aleksandar Dogandžić

Many normalizing flow architectures impose regularity constraints, yet their distributional approximation properties are not fully characterized. We study the expressivity of bi-Lipschitz normalizing flows through the lens of score-based…

Machine Learning · Statistics 2026-05-08 Meira Iske , Carola-Bibiane Schönlieb