English
Related papers

Related papers: The strong data processing inequality under the he…

200 papers

Heat fluctuations over a time \tau in a non-equilibrium stationary state and in a transient state are studied for a simple system with deterministic and stochastic components: a Brownian particle dragged through a fluid by a harmonic…

Statistical Mechanics · Physics 2007-05-23 R. van Zon , E. G. D. Cohen

This paper provides a detailed analysis of the lower deviation probability properties for a $d$-type ($d>1$) Galton--Watson (GW) process $\{\textbf{Z}_n=(Z_n^{(i)})_{1\le i\le d};n\ge0\}$ in both Schr\"{o}der and B\"{o}ttcher cases. We…

Probability · Mathematics 2025-07-01 Tan Jiangrui

The aim of this paper is to establish the uniform convergence of the densities of a sequence of random variables, which are functionals of an underlying Gaussian process, to a normal density. Precise estimates for the uniform distance are…

Probability · Mathematics 2013-08-30 Yaozhong Hu , Fei Lu , David Nualart

We investigate a one dimensional chain of $2N$ harmonic oscillators in which neighboring sites have their energies redistributed randomly. The sites $-N$ and $N$ are in contact with thermal reservoirs at different temperature $\tau_-$ and…

Statistical Mechanics · Physics 2009-11-11 Lorenzo Bertini , Davide Gabrielli , Joel L. Lebowitz

Score-based generative models have emerged as a powerful approach for sampling high-dimensional probability distributions. Despite their effectiveness, their theoretical underpinnings remain relatively underdeveloped. In this work, we study…

Machine Learning · Computer Science 2025-04-22 Daniel Zhengyu Huang , Jiaoyang Huang , Zhengjiang Lin

The behavior of slow-fast diffusions as the separation of scale diverges is a well-studied problem in the literature. In this short paper, we revisit this problem and obtain a new proof of existing strong quantitative convergence estimates…

Optimization and Control · Mathematics 2025-10-28 Sumith Reddy Anugu , Vivek S. Borkar

Gradient-flow sampling interprets a Gibbs distribution as the minimizer of an energy functional over probability measures and generates dynamics converging to this target. Under spherical Hellinger-Kantorovich (SHK) geometry, the flow…

Machine Learning · Statistics 2026-05-25 Aratrika Mustafi , Soumya Mukherjee

Density destructors are differentiable and invertible transforms that map multivariate PDFs of arbitrary structure (low entropy) into non-structured PDFs (maximum entropy). Multivariate Gaussianization and multivariate equalization are…

Machine Learning · Statistics 2020-12-03 J. Emmanuel Johnson , Valero Laparra , Gustau Camps-Valls , Raul Santos-Rodríguez , Jesús Malo

Denoising Diffusion Probabilistic Models (DDPM) are powerful state-of-the-art methods used to generate synthetic data from high-dimensional data distributions and are widely used for image, audio, and video generation as well as many more…

Machine Learning · Statistics 2025-04-25 Iskander Azangulov , George Deligiannidis , Judith Rousseau

We consider the steady heat transfer between a collection of impermeable obstacles immersed in an incompressible 2D potential flow, when each obstacle has a prescribed boundary temperature distribution. Inside the fluid, the temperature…

Fluid Dynamics · Physics 2025-09-12 Kyle McKee , Keaton Burns

The families of $f$-divergences (e.g. the Kullback-Leibler divergence) and Integral Probability Metrics (e.g. total variation distance or maximum mean discrepancies) are widely used to quantify the similarity between probability…

Statistics Theory · Mathematics 2021-06-08 Rohit Agrawal , Thibaut Horel

Gaussian Processes and the Kullback-Leibler divergence have been deeply studied in Statistics and Machine Learning. This paper marries these two concepts and introduce the local Kullback-Leibler divergence to learn about intervals where two…

Methodology · Statistics 2023-07-13 Nicolás Hernández , Gabriel Martos

This paper studies sampling error bounds for denoising diffusion probabilistic models (DDPMs) in the 2-Wasserstein distance. Our contributions are threefold. (i) Under general Lipschitz-type conditions on the score function and for a broad…

Machine Learning · Statistics 2026-05-19 Yuta Koike

We consider the standard first passage percolation model in $\mathbb{Z}^d$ for $d\geq 2$. We are interested in two quantities, the maximal flow $\tau$ between the lower half and the upper half of the box, and the maximal flow $\phi$ between…

Probability · Mathematics 2009-07-03 Raphaël Rossignol , Marie Théret

We study the large deviations performance, i.e., the exponential decay rate of the error probability, of distributed detection algorithms over random networks. At each time step $k$ each sensor: 1) averages its decision variable with the…

Information Theory · Computer Science 2010-12-22 Dragana Bajovic , Dusan Jakovetic , Joao Xavier , Bruno Sinopoli , Jose M. F. Moura

We provide improved differentially private algorithms for identity testing of high-dimensional distributions. Specifically, for $d$-dimensional Gaussian distributions with known covariance $\Sigma$, we can test whether the distribution…

Data Structures and Algorithms · Computer Science 2022-07-26 Shyam Narayanan

We investigate the entropy $H(\mu,t)$ of a probability measure $\mu$ along the heat flow and more precisely we seek for closed algebraic representations of its derivatives. Provided that $\mu$ admits moments of any order, it is indeed…

Information Theory · Computer Science 2024-06-18 Paul Mansanarez , Guillaume Poly , Yvik Swan

Quantifying changes in the probability and magnitude of extreme flooding events is key to mitigating their impacts. While hydrodynamic data are inherently spatially dependent, traditional spatial models such as Gaussian processes are poorly…

Methodology · Statistics 2024-05-06 Reetam Majumder , Brian J. Reich , Benjamin A. Shaby

In this tutorial, we aim to directly recreate some of our "aha" moments when exploring the impact of heat diffusion on the spatial resolution limit of photothermal imaging. Our objective is also to communicate how this physical limit can…

Numerical Analysis · Mathematics 2024-06-12 Peter Burgholzer , Günther Mayr , Gregor Thummerer , Markus Haltmeier

Diffusion models have demonstrated remarkable empirical success in the recent years and are considered one of the state-of-the-art generative models in modern AI. These models consist of a forward process, which gradually diffuses the data…

Machine Learning · Computer Science 2026-01-07 Xingyu Xu , Ziyi Zhang , Yorie Nakahira , Guannan Qu , Yuejie Chi