English
Related papers

Related papers: Taming under isoperimetry

200 papers

We study sampling from a target distribution ${\nu_* = e^{-f}}$ using the unadjusted Langevin Monte Carlo (LMC) algorithm. For any potential function $f$ whose tails behave like ${\|x\|^\alpha}$ for ${\alpha \in [1,2]}$, and has…

Machine Learning · Statistics 2020-05-28 Murat A. Erdogdu , Rasa Hosseinzadeh

This paper introduces a new constraint-free concave dual formulation for the Wasserstein barycenter. Tailoring the vanilla dual gradient ascent algorithm to the Sobolev geometry, we derive a scalable Sobolev gradient ascent (SGA) algorithm…

Optimization and Control · Mathematics 2026-04-21 Kaheon Kim , Bohan Zhou , Changbo Zhu , Xiaohui Chen

We consider a generic and explicit tamed Euler--Maruyama scheme for multidimensional time-inhomogeneous stochastic differential equations with multiplicative Brownian noise. The diffusive coefficient is uniformly elliptic, H\"older…

Probability · Mathematics 2025-02-03 Khoa Lê , Chengcheng Ling

We derive weighted log-Sobolev inequalities from a class of super Poincar\'e inequalities. As an application, the Talagrand inequality with larger distances are obtained. In particular, on a complete connected Riemannian manifold, we prove…

Probability · Mathematics 2007-12-20 Feng-Yu Wang

We discuss our work on pointwise inequalities for the gradient which are connected with the isoperimetric profile associated to a given geometry. We show how they can be used to unify certain aspects of the theory of Sobolev inequalities.…

Functional Analysis · Mathematics 2014-04-17 Joaquim Martin , Mario Milman

Estimation of solution norms and stability for time-dependent nonlinear systems is ubiquitous in numerous applied and control problems. Yet, practically valuable results are rare in this area. This paper develops a novel approach, which…

Dynamical Systems · Mathematics 2018-08-29 Mark A. Pinsky , Steve Koblik

This work considers the problem of sampling from a probability distribution known up to a normalization constant while satisfying a set of statistical constraints specified by the expected values of general nonlinear functions. This problem…

Machine Learning · Statistics 2025-01-08 Luiz F. O. Chamon , Mohammad Reza Karimi , Anna Korba

The kinetic Langevin dynamics finds diverse applications in various disciplines such as molecular dynamics and Hamiltonian Monte Carlo sampling. In this paper, a novel splitting scalar auxiliary variable (SSAV) scheme is proposed for the…

Numerical Analysis · Mathematics 2025-09-05 Lei Dai , Yingsong Jiang , Xiaojie Wang

We study Slowly Annealed Langevin Dynamics (SALD), a sampler for tracking a path of moving target distributions and approximating the terminal target through time slowdown. We establish non-asymptotic convergence guarantees via a KL…

Machine Learning · Computer Science 2026-05-11 Atsushi Nitanda , Dake Bu , Yueming Lyu , Tanya Veeravalli

We address the Unsupervised Domain Adaptation (UDA) problem in image classification from a new perspective. In contrast to most existing works which either align the data distributions or learn domain-invariant features, we directly learn a…

Computer Vision and Pattern Recognition · Computer Science 2020-12-03 Qian Wang , Fanlin Meng , Toby P. Breckon

We study the equations obtained from linearizing the compressible Navier-Stokes equations around a steady-state profile with a heavier fluid lying above a lighter fluid along a planar interface, i.e. a Rayleigh-Taylor instability. We…

Analysis of PDEs · Mathematics 2009-11-25 Yan Guo , Ian Tice

We consider a diffusion on a potential landscape which is given by a smooth Hamiltonian $H:\mathbb {R}^n\to \mathbb {R}$ in the regime of low temperature $\varepsilon$. We proof the Eyring-Kramers formula for the optimal constant in the…

Probability · Mathematics 2016-08-14 Georg Menz , André Schlichting

Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows…

Machine Learning · Computer Science 2017-06-06 Maxim Raginsky , Alexander Rakhlin , Matus Telgarsky

In this paper we show that the weighted Bernstein-Walsh inequality in logarithmic potential theory is sharp up to some new universal constant, provided that the external field is given by a logarithmic potential. Our main tool for such…

Numerical Analysis · Mathematics 2017-07-26 Bernhard Beckermann , Thomas Helart

The present work concerns spherical spin glass models with disorder satisfying a uniform logarithmic Sobolev inequality. We show that the Hessian descent algorithm introduced by Subag can be extended to this setting, thanks to the abundance…

Probability · Mathematics 2025-05-07 Fu-Hsuan Ho

We study the mixing time of Metropolis-Adjusted Langevin algorithm (MALA) for sampling a target density on $\mathbb{R}^d$. We assume that the target density satisfies $\psi_\mu$-isoperimetry and that the operator norm and trace of its…

Machine Learning · Statistics 2023-06-09 Yuansi Chen , Khashayar Gatmiry

We find sufficient conditions for a probability measure $\mu$ to satisfy an inequality of the type $$ \int_{\R^d} f^2 F\Bigl(\frac{f^2}{\int_{\R^d} f^2 d \mu} \Bigr) d \mu \le C \int_{\R^d} f^2 c^{*}\Bigl(\frac{|\nabla f|}{|f|} \Bigr) d \mu…

Probability · Mathematics 2007-05-23 Alexander V. Kolesnikov

We study stability under tensorization and projection-type operations of gradient-type estimates and other functional inequalities for Markov semigroups on metric spaces. Using transportation-type inequalities obtained by F. Baudoin and N.…

Probability · Mathematics 2025-01-03 Fabrice Baudoin , Maria Gordina , Rohan Sarkar

Building on the inequalities for homogeneous tetrahedral polynomials in independent Gaussian variables due to R. Lata{\l}a we provide a concentration inequality for non-necessarily Lipschitz functions $f\colon \R^n \to \R$ with bounded…

Probability · Mathematics 2013-04-09 Radosław Adamczak , Paweł Wolff

We study the problem of non-convex optimization using Stochastic Gradient Langevin Dynamics (SGLD). SGLD is a natural and popular variation of stochastic gradient descent where at each step, appropriately scaled Gaussian noise is added. To…

Machine Learning · Computer Science 2024-07-08 August Y. Chen , Ayush Sekhari , Karthik Sridharan