English
Related papers

Related papers: Small Deviation Probability via Chaining

200 papers

We study the small deviation probabilities of a family of very smooth self-similar Gaussian processes. The canonical process from the family has the same scaling property as standard Brownian motion and plays an important role in the study…

Probability · Mathematics 2011-08-18 Frank Aurzada , Fuchang Gao , Thomas Kühn , Wenbo V. Li , Qi-Man Shao

We investigate the small deviation probabilities of a class of very smooth stationary Gaussian processes playing an important role in Bayesian statistical inference. Our calculations are based on the appropriate modification of the entropy…

Probability · Mathematics 2010-06-22 F. Aurzada , I. A. Ibragimov , M. A. Lifshits , J. H. van Zanten

We show that classical chaining bounds on the suprema of random processes in terms of entropy numbers can be systematically improved when the underlying set is convex: the entropy numbers need not be computed for the entire set, but only…

Probability · Mathematics 2023-09-18 Ramon van Handel

We give two examples of periodic Gaussian processes, having entropy numbers of exactly same order but radically different small deviations. Our construction is based on classical Knopp's result yielding of existence of continuous nowhere…

Probability · Mathematics 2017-07-13 Michel Weber

We modify Talagrand's generic chaining method to obtain upper bounds for all p-th moments of the supremum of a stochastic process. These bounds lead to an estimate for the upper tail of the supremum with optimal deviation parameters. We…

Probability · Mathematics 2014-03-25 Sjoerd Dirksen

We use the generic chaining device proposed by Talagrand to establish exponential bounds on the deviation probability of some suprema of random processes. Then, given a random vector $\xi$ in $\R^{n}$ the components of which are independent…

Statistics Theory · Mathematics 2009-04-22 Yannick Baraud

Gaussian process regression (GPR) is a popular nonparametric Bayesian method that provides predictive uncertainty estimates and is widely used in safety-critical applications. While prior research has introduced various uncertainty bounds,…

Machine Learning · Computer Science 2025-12-05 Junyi Liu , Stanley Kok

Deep Gaussian processes provide a flexible approach to probabilistic modelling of data using either supervised or unsupervised learning. For tractable inference approximations to the marginal likelihood of the model must be made. The…

Machine Learning · Statistics 2014-12-04 James Hensman , Neil D. Lawrence

The paper deals with the asymptotic behavior of the bridge of a Gaussian process conditioned to stay in $n$ fixed points at $n$ fixed past instants. In particular, functional large deviation results are stated for small time. Several…

Probability · Mathematics 2016-04-06 L. Caramellino , B. Pacchiarotti

This paper extends the standard chaining technique to prove excess risk upper bounds for empirical risk minimization with random design settings even if the magnitude of the noise and the estimates is unbounded. The bound applies to many…

Machine Learning · Statistics 2016-09-08 Gábor Balázs , András György , Csaba Szepesvári

We consider the small deviation probabilities (SDP) for sums of stationary Gaussian sequences. For the cases of constant boundaries and boundaries tending to zero, we obtain quite general results. For the case of the boundaries tending to…

Probability · Mathematics 2020-02-11 Frank Aurzada , Mikhail Lifshits

Lower bounds for persistence probabilities of stationary Gaussian processes in discrete time are obtained under various conditions on the spectral measure of the process. Examples are given to show that the persistence probability can decay…

Probability · Mathematics 2016-02-02 Krishna M. , Manjunath Krishnapur

We present a new lower bound on the differential entropy rate of stationary processes whose sequences of probability density functions fulfill certain regularity conditions. This bound is obtained by showing that the gap between the…

Information Theory · Computer Science 2017-08-30 Meik Dörpinghaus

We construct intrinsic on-and off-diagonal upper and lower estimates for the transition probability density of a L\'evy process in small time. By intrinsic we mean that such estimates reflect the structure of the characteristic exponent of…

Probability · Mathematics 2013-08-09 Victoria Knopova , Alexei Kulik

Stochastic gradient descent (SGD) and its variants have established themselves as the go-to algorithms for large-scale machine learning problems with independent samples due to their generalization performance and intrinsic computational…

Machine Learning · Statistics 2025-08-25 Hao Chen , Lili Zheng , Raed Al Kontar , Garvesh Raskutti

We address the choice of the tuning parameter $\lambda$ in $\ell_1$-penalized M-estimation. Our main concern is models which are highly nonlinear, such as the Gaussian mixture model. The number of parameters $p$ is moreover large, possibly…

Statistics Theory · Mathematics 2012-05-17 Sara van de Geer

We consider the problem of inferring a latent function in a probabilistic model of data. When dependencies of the latent function are specified by a Gaussian process and the data likelihood is complex, efficient computation often involve…

Machine Learning · Statistics 2018-07-23 Martin Tegner , Benjamin Bloem-Reddy , Stephen Roberts

We investigate the Large Deviation behavior in small time of continuous Gaussian processes. We introduce a general procedure allowing to derive Large Deviation Principles in small time starting from the well understood context of Large…

Probability · Mathematics 2023-01-11 Paolo Baldi , Barbara Pacchiarotti

Gaussian process models are flexible, Bayesian non-parametric approaches to regression. Properties of multivariate Gaussians mean that they can be combined linearly in the manner of additive models and via a link function (like in…

Machine Learning · Statistics 2016-04-19 Alan D. Saul , James Hensman , Aki Vehtari , Neil D. Lawrence

We use rescaled Gaussian processes as prior models for functional parameters in nonparametric statistical models. We show how the rate of contraction of the posterior distributions depends on the scaling factor. In particular, we exhibit…

Statistics Theory · Mathematics 2009-09-29 Aad van der Vaart , Harry van Zanten
‹ Prev 1 2 3 10 Next ›