English
Related papers

Related papers: Generalised Pinsker Inequalities

200 papers

Problems of calculus of variations with variable endpoints cannot be solved without transversality conditions. Here, we establish such type of conditions for fractional variational problems with the Caputo derivative. We consider: the…

Optimization and Control · Mathematics 2015-06-05 Ricardo Almeida , Agnieszka B. Malinowska

We introduce two new classes of measures of information for statistical experiments which generalise and subsume $\phi$-divergences, integral probability metrics, $\mathfrak{N}$-distances (MMD), and $(f,\Gamma)$ divergences between two or…

Machine Learning · Computer Science 2023-09-11 Robert C. Williamson , Zac Cranko

We propose the use of algebras of generalized functions for the analysis of certain highly singular problems in the calculus of variations. After a general study of extremal problems on open subsets of Euclidean space in this setting we…

Functional Analysis · Mathematics 2008-09-11 Sanja Konjik , Michael Kunzinger , Michael Oberguggenberger

We propose a general algorithm for approximating nonstandard Bayesian posterior distributions. The algorithm minimizes the Kullback-Leibler divergence of an approximating distribution to the intractable posterior distribution. Our method…

Computation · Statistics 2014-07-29 Tim Salimans , David A. Knowles

Deep neural networks (DNNs) exhibit an exceptional capacity for generalization in practical applications. This work aims to capture the effect and benefits of depth for supervised learning via information-theoretic generalization bounds. We…

Machine Learning · Computer Science 2025-05-09 Haiyun He , Ziv Goldfeld

A central question in causal inference with observational studies is the sensitivity of conclusions to unmeasured confounding. The classical Cornfield condition allows us to assess whether an unmeasured binary confounder can explain away…

Applications · Statistics 2014-04-30 Peng Ding , Tyler J. VanderWeele

We study a fuzzy Boltzmann equation, where particles interact via delocalised collisions, in contrast to classical Boltzmann equations. We discuss the existence and uniqueness of solutions and provide a natural variational characterisation…

Analysis of PDEs · Mathematics 2024-04-19 Matthias Erbar , Zihui He

Various approaches have been developed to upper bound the generalization error of a supervised learning algorithm. However, existing bounds are often loose and even vacuous when evaluated in practice. As a result, they may fail to…

Information Theory · Computer Science 2022-10-19 Gholamali Aminian , Yuheng Bu , Laura Toni , Miguel R. D. Rodrigues , Gregory W. Wornell

The main result is a generalization of Keller's recursion equation for finding a prime number given the previous primes. We also examine the convergence of the limit in Keller's equation and the convergence of the limit in the general…

Number Theory · Mathematics 2013-11-19 James Haley

We propose a simple approach that provides accurate uncertainty quantification for Bayesian inference in misspecified or approximate models, and for generalized (Gibbs) posteriors. While existing solutions in this context are based on…

Methodology · Statistics 2026-03-11 David T. Frazier , Christopher Drovandi , Robert Kohn

Wide conditions are provided to guarantee asymptotic unbiasedness and L^2-consistency of the introduced estimates of the Kullback-Leibler divergence for probability measures in R^d having densities w.r.t. the Lebesgue measure. These…

Statistics Theory · Mathematics 2019-07-02 Alexander Bulinski , Denis Dimitrov

A complete solution to the multiplier version of the inverse problem of the calculus of variations is given for a class of hyperbolic systems of second-order partial differential equations in two independent variables. The necessary and…

Differential Geometry · Mathematics 2009-10-16 Matt Biesecker

The center of interest in this work are variational problems with integral functionals depending on special nonlocal gradients. The latter correspond to truncated versions of the Riesz fractional gradient, as introduced in [Bellido, Cueto &…

Analysis of PDEs · Mathematics 2023-04-18 Javier Cueto , Carolin Kreisbeck , Hidde Schönberger

We extend the classical Bernstein inequality to a general setting including Schr{\"o}dinger operators and divergence form elliptic operators on Riemannian manifolds or domains. Moreover , we prove a new reverse inequality that can be seen…

Analysis of PDEs · Mathematics 2021-06-11 Rafik Imekraz , El Maati Ouhabaz

We introduce new natural generalizations of the classical descent and inversion statistics for permutations, called width-$k$ descents and width-$k$ inversions. These variations induce generalizations of the excedance and major statistics,…

Combinatorics · Mathematics 2017-01-18 Robert Davis

Recent work has attempted to directly approximate the `function-space' or predictive posterior distribution of Bayesian models, without approximating the posterior distribution over the parameters. This is appealing in e.g. Bayesian neural…

Machine Learning · Statistics 2020-11-19 David R. Burt , Sebastian W. Ober , Adrià Garriga-Alonso , Mark van der Wilk

In this paper, some new upper bounds for Kullback-Leibler divergence(KL-divergence) based on $L^1, L^2$ and $L^\infty$ norms of density functions are discussed. Our findings unveil that the convergence in KL-divergence sense sandwiches…

Probability · Mathematics 2024-10-31 Liuquan Yao , Songhao Liu

We investigate the use of alternative divergences to Kullback-Leibler (KL) in variational inference(VI), based on the Variational Dropout \cite{kingma2015}. Stochastic gradient variational Bayes (SGVB) \cite{aevb} is a general framework for…

Machine Learning · Statistics 2017-11-15 Bogdan Mazoure , Riashat Islam

In this work, a generalization of the well known Bernoulli inequality is obtained by using the theory of discrete fractional calculus. As far as we know our approach is novel.

Classical Analysis and ODEs · Mathematics 2017-08-29 Rui A. C. Ferreira

A new bimodal generative model is proposed for generating conditional and joint samples, accompanied with a training method with learning a succinct bottleneck representation. The proposed model, dubbed as the variational Wyner model, is…

Machine Learning · Computer Science 2022-07-29 J. Jon Ryu , Yoojin Choi , Young-Han Kim , Mostafa El-Khamy , Jungwon Lee