English
Related papers

Related papers: Predictive Information Rate in Discrete-time Gauss…

200 papers

We consider the problem of noisy private information retrieval (NPIR) from $N$ non-communicating databases, each storing the same set of $M$ messages. In this model, the answer strings are not returned through noiseless bit pipes, but…

Information Theory · Computer Science 2018-07-17 Karim Banawan , Sennur Ulukus

Private information retrieval (PIR) is a mechanism for efficiently downloading messages while keeping the index of the desired message secret from the servers. PIR schemes have been extended to various scenarios with adversarial servers:…

Information Theory · Computer Science 2026-01-23 Atsushi Miki , Toshiyasu Matsushima

We define the information threshold as the point of maximum curvature in the prior vs. posterior Bayesian curve, both of which are described as a function of the true positive and negative rates of the classification system in question. The…

Machine Learning · Statistics 2022-06-07 Jacques Balayla

In many real world problems, control decisions have to be made with limited information. The controller may have no a priori (or even posteriori) data on the nonlinear system, except from a limited number of points that are obtained over…

Optimization and Control · Mathematics 2011-05-12 Tansu Alpcan

In this paper, we discuss the convergence rate of empirical processes of Gaussian processes for a large class of function families. Our main goal is to show that the tail of the uniform norm of the empirical processes can be dominated by…

Probability · Mathematics 2023-03-22 Wen Huo , Yasutaka Shimizu

The Principle of Insufficient Reason (PIR) assigns equal probabilities to each alternative of a random experiment whenever there is no reason to prefer one over the other. The Maximum Entropy Principle (MaxEnt) generalizes PIR to the case…

Machine Learning · Statistics 2021-11-25 Dominik Janzing

This paper characterizes the impact of covariate serial dependence on the non-asymptotic estimation error bound of penalized regressions (PRs). Focusing on the direct relationship between the degree of cross-correlation between covariates…

Statistics Theory · Mathematics 2023-02-14 Simone Tonini , Francesca Chiaromonte , Alessandro Giovannelli

We rigorously prove that deep Gaussian process priors can outperform Gaussian process priors if the target function has a compositional structure. To this end, we study information-theoretic lower bounds for posterior contraction rates for…

Machine Learning · Statistics 2022-09-28 Matteo Giordano , Kolyan Ray , Johannes Schmidt-Hieber

The performance of Gaussian Process (GP) regression is often hampered by the curse of dimensionality, which inflates computational cost and reduces predictive power in high-dimensional problems. Variable selection is thus crucial for…

Methodology · Statistics 2025-11-24 Minshen Xu , Shiwei Lan , Lulu Kang

We consider private information retrieval (PIR) for distributed storage systems (DSSs) with noncolluding nodes where data is stored using a non maximum distance separable (MDS) linear code. It was recently shown that if data is stored using…

Information Theory · Computer Science 2018-09-19 Hsuan-Yin Lin , Siddhartha Kumar , Eirik Rosnes , Alexandre Graell i Amat

Gaussian Processes (GPs) can be used as flexible, non-parametric function priors. Inspired by the growing body of work on Normalizing Flows, we enlarge this class of priors through a parametric invertible transformation that can be made…

Machine Learning · Computer Science 2021-02-26 Juan Maroñas , Oliver Hamelijnck , Jeremias Knoblauch , Theodoros Damoulas

Gaussian process regression is a frequently used statistical method for flexible yet fully probabilistic non-linear regression modeling. A common obstacle is its computational complexity which scales poorly with the number of observations.…

Methodology · Statistics 2026-03-10 Adam Gorm Hoffmann , Claus Thorn Ekstrøm , Andreas Kryger Jensen

Gaussian processes (GPs) are ubiquitous tools for modeling and predicting continuous processes in physical and engineering sciences. This is partly due to the fact that one may employ a Gaussian process as an interpolator while facilitating…

Statistics Theory · Mathematics 2025-12-16 D. Andrew Brown , Peter Kiessler , John Nicholson

The information rates achievable by using electromagnetic radiation affected by thermal noise and signal decoherence are studied. The standard coherent Gaussian model is compared with an alternative photon gas model which represents lack of…

Quantum Physics · Physics 2007-08-13 Alfonso Martinez

When complex Bayesian models exhibit implausible behaviour, one solution is to assemble available information into an informative prior. Challenges arise as prior information is often only available for the observable quantity, or some…

Methodology · Statistics 2026-03-18 Andrew A. Manderson , Robert J. B. Goudie

Gaussian process regression is widely used because of its ability to provide well-calibrated uncertainty estimates and handle small or sparse datasets. However, it struggles with high-dimensional data. One possible way to scale this…

Machine Learning · Statistics 2024-02-02 Bernardo Fichera , Viacheslav Borovitskiy , Andreas Krause , Aude Billard

We consider the information fiber optical channel modeled by the nonlinear Schrodinger equation with additive Gaussian noise. Using path-integral approach and perturbation theory for the small dimensionless parameter of the second…

Information Theory · Computer Science 2023-08-03 A. V. Reznichenko , V. O. Guba

Private Information Retrieval (PIR) allows clients to retrieve database entries without leaking retrieval indices, yet malicious servers seriously compromise retrieval correctness. Existing Authenticated PIR (APIR) schemes resist…

Cryptography and Security · Computer Science 2026-04-27 Pengzhen Ke , Yuxuan Qin , Liang Feng Zhang

The use of Gaussian process models is typically limited to datasets with a few tens of thousands of observations due to their complexity and memory footprint. The two most commonly used methods to overcome this limitation are 1) the…

Machine Learning · Statistics 2020-01-16 Vincent Adam , Stefanos Eleftheriadis , Nicolas Durrande , Artem Artemev , James Hensman

We advocate for a new statistical principle that combines the most desirable aspects of both parameter inference and density estimation. This leads us to the predictively oriented (PrO) posterior, which expresses uncertainty as a…

‹ Prev 1 4 5 6 7 8 10 Next ›