English
Related papers

Related papers: Large Deviation Principle for Enhanced Gaussian Pr…

200 papers

We establish a large deviation principle for the trajectories of Wiener processes subject to random resets to the origin occurring according to a Poisson process. In addition to the pathwise large deviation principle, we identify the rate…

Probability · Mathematics 2025-12-09 A. V. Logachov , O. M. Logachova , A. A. Yambartsev , K. A. Zaykov

In this paper, we consider forward-backward stochastic differential equation driven by $G$-Brownian motion ($G$-FBSDEs in short) with small parameter $\varepsilon > 0$. We study the asymptotic behavior of the solution of the backward…

Probability · Mathematics 2020-03-27 Ibrahim Dakaou , Abdoulaye Soumana Hima

A general class of non-Markov, supercritical Gaussian branching particle systems is introduced and its long-time asymptotics is studied. Both weak and strong laws of large numbers are developed with the limit object being characterized in…

Probability · Mathematics 2018-07-30 Michael A. Kouritzin , Khoa Lê , Deniz Sezer

We introduce stochastic variational inference for Gaussian process models. This enables the application of Gaussian process (GP) models to data sets containing millions of data points. We show how GPs can be vari- ationally decomposed to…

Machine Learning · Computer Science 2013-09-27 James Hensman , Nicolo Fusi , Neil D. Lawrence

The process $(G_t)_{t\in[0,T]}$ is referred to as a fractional Gaussian process if the first-order partial derivative of the difference between its covariance function and that of the fractional Brownian motion $(B^H_t)_{t\in[0,T ]}$ is a…

Probability · Mathematics 2023-09-20 Yong Chen , Ying Li

A large deviations principle is established for the joint law of the empirical measure and the flow measure of a renewal Markov process on a finite graph. We do not assume any bound on the arrival times, allowing heavy tailed distributions.…

Probability · Mathematics 2014-02-18 Mauro Mariani , Lorenzo Zambotti

Multifidelity models integrate data from multiple sources to produce a single approximator for the underlying process. Dense low-fidelity samples are used to reduce interpolation error, while sparse high-fidelity samples are used to…

Machine Learning · Statistics 2024-02-27 Viv Bone , Chris van der Heide , Kieran Mackle , Ingo H. J. Jahn , Peter M. Dower , Chris Manzie

In this paper, we present a large-deviation theory developed for functionals of canonical Gibbs processes, i.e., Gibbs processes with respect to the binomial point process. We study the regime of a fixed intensity in a sequence of…

Probability · Mathematics 2025-05-29 Christian Hirsch , Martina Petráková

Gaussian processes (GPs) are a powerful tool for probabilistic inference over functions. They have been applied to both regression and non-linear dimensionality reduction, and offer desirable properties such as uncertainty estimates,…

Machine Learning · Statistics 2014-10-01 Yarin Gal , Mark van der Wilk , Carl E. Rasmussen

In this paper, we present a sufficient condition for the large deviation criteria of Budhiraja, Dupuis and Maroulas for functionals of Brownian motions. We then establish a large deviation principle for obstacle problems of quasi-linear…

Probability · Mathematics 2017-12-07 Anis Matoussi , Wissal Sabbagh , Tusheng Zhang

We establish a large-deviations principle for the largest eigenvalue of a generalized sample covariance matrix, meaning a matrix proportional to $Z^T \Gamma Z$, where $Z$ has i.i.d. real or complex entries and $\Gamma$ is not necessarily…

Probability · Mathematics 2023-02-07 Jonathan Husson , Benjamin McKenna

We revisit Wschebor's theorems on small increments for processes with scaling and stationary properties and deduce large deviation principles.

Probability · Mathematics 2019-07-05 Jose R. Leon , José León , Alain Rouault

The theory of large deviations constitutes a mathematical cornerstone in the foundations of Boltzmann-Gibbs statistical mechanics, based on the additive entropy $S_{BG}=- k_B\sum_{i=1}^W p_i \ln p_i$. Its optimization under appropriate…

Statistical Mechanics · Physics 2011-10-31 Guiomar Ruiz , Constantino Tsallis

Bayesian learning using Gaussian processes provides a foundational framework for making decisions in a manner that balances what is known with what could be learned by gathering data. In this dissertation, we develop techniques for…

Machine Learning · Statistics 2022-04-29 Alexander Terenin

This paper gives a brief introduction to some important fractional and multifractional Gaussian processes commonly used in modelling natural phenomena and man-made systems. The processes include fractional Brownian motion (both standard and…

Mathematical Physics · Physics 2014-07-01 S. C. Lim , C. H. Eab

We prove a large deviations principle for the empirical law of the block sizes of a uniformly distributed non-crossing partition. As an application we obtain a variational formula for the maximum of the support of a compactly supported…

Probability · Mathematics 2011-07-04 Janosch Ortmann

We establish large deviation principles for the couple of the maximum likelihood estimators of dimensional and drift coefficients in the generalised squared radial Ornstein-Uhlenbeck process. We focus our attention to the most tractable…

Probability · Mathematics 2016-11-28 Marie du Roy de Chaumaray

We study wide Bayesian neural networks focusing on the rare but statistically dominant fluctuations that govern posterior concentration, beyond Gaussian-process limits. Large-deviation theory provides explicit variational objectives-rate…

Machine Learning · Statistics 2026-02-27 Katerina Papagiannouli , Dario Trevisan , Giuseppe Pio Zitto

Under certain mild conditions, some limit theorems for functionals of two independent Gaussian processes are obtained. The results apply to general Gaussian processes including fractional Brownian motion, sub-fractional Brownian motion and…

Probability · Mathematics 2018-01-30 Jian Song , Fangjun Xu , Qian Yu

We consider large deviations of empirical measures of diffusion processes. In a first part, we present conditions to obtain a large deviations principle (LDP) for a precise class of unbounded functions. This provides an analogue to the…

Probability · Mathematics 2020-09-23 Grégoire Ferré , Gabriel Stoltz