English
Related papers

Related papers: Relative Information Loss - An Introduction

200 papers

We investigate the analogy between the renormalization group (RG) and deep neural networks, wherein subsequent layers of neurons are analogous to successive steps along the RG. In particular, we quantify the flow of information by…

High Energy Physics - Theory · Physics 2021-12-22 Johanna Erdmenger , Kevin T. Grosvenor , Ro Jefferson

We present a unifying picture of PAC-Bayesian and mutual information-based upper bounds on the generalization error of randomized learning algorithms. As we show, Tong Zhang's information exponential inequality (IEI) gives a general recipe…

Machine Learning · Computer Science 2021-10-26 Pradeep Kr. Banerjee , Guido Montúfar

This paper introduces "swiveled Renyi entropies" as an alternative to the Renyi entropic quantities put forward in [Berta et al., Phys. Rev. A 91, 022333 (2015)]. What distinguishes the swiveled Renyi entropies from the prior proposal of…

Quantum Physics · Physics 2016-03-22 Frédéric Dupuis , Mark M. Wilde

A well-known technique in estimating probabilities of rare events in general and in information theory in particular (used, e.g., in the sphere-packing bound), is that of finding a reference probability measure under which the event of…

Information Theory · Computer Science 2014-12-23 Rami Atar , Neri Merhav

This paper considers structural optimization under a reliability constraint, where the input distribution is only partially known. Specifically, when we only know that the expected value vector and the variance-covariance matrix of the…

Optimization and Control · Mathematics 2022-12-19 Yoshihiro Kanno

Using established principles from Statistics and Information Theory, we show that invariance to nuisance factors in a deep neural network is equivalent to information minimality of the learned representation, and that stacking layers and…

Machine Learning · Computer Science 2018-06-29 Alessandro Achille , Stefano Soatto

We show how convergence to the Gumbel distribution in an extreme value setting can be understood in an information-theoretic sense. We introduce a new type of score function which behaves well under the maximum operation, and which implies…

Statistics Theory · Mathematics 2024-07-22 Oliver Johnson

Information generating functions have been used for generating various entropy and divergence measures. In the present work, we introduce quantile based relative information generating function and study its properties. The proposed…

Statistics Theory · Mathematics 2024-12-04 Sankaran P. G. , Sunoj S. M. , Pavithra Hariharan

We provide a new information-theoretic generalization error bound that is exactly tight (i.e., matching even the constant) for the canonical quadratic Gaussian (location) problem. Most existing bounds are order-wise loose in this setting,…

Information Theory · Computer Science 2023-11-14 Ruida Zhou , Chao Tian , Tie Liu

We integrate information-theoretic concepts into the design and analysis of optimistic algorithms and Thompson sampling. By making a connection between information-theoretic quantities and confidence bounds, we obtain results that relate…

Machine Learning · Statistics 2019-11-25 Xiuyuan Lu , Benjamin Van Roy

Neural networks used for multi-interaction trajectory reconstruction lack the ability to estimate the uncertainty in their outputs, which would be useful to better analyse and understand the systems they model. In this paper we extend the…

Machine Learning · Computer Science 2020-06-26 Vasileios Karavias , Ben Day , Pietro Liò

The aim of this work is to provide bounds connecting two probability measures of the same event using R\'enyi $\alpha$-Divergences and Sibson's $\alpha$-Mutual Information, a generalization of respectively the Kullback-Leibler Divergence…

Information Theory · Computer Science 2020-01-20 Amedeo Roberto Esposito , Michael Gastpar , Ibrahim Issa

We propose R\'enyi information generating function and discuss its properties. A connection between the R\'enyi information generating function and the diversity index is proposed for discrete type random variables. The relation between the…

Statistics Theory · Mathematics 2025-02-25 Shital Saha , Suchandan Kayal , N. Balakrishnan

Learning depends on the ability to acquire and assimilate new information. This ability depends---somewhat counterintuitively---on the ability to forget. In particular, effective forgetting requires the ability to recognize and utilize new…

Optimization and Control · Mathematics 2021-04-05 Ankit Goel , Adam L. Bruce , Dennis S. Bernstein

Information theory has become an increasingly important research field to better understand quantum mechanics. Noteworthy, it covers both foundational and applied perspectives, also offering a common technical language to study a variety of…

Quantum Physics · Physics 2021-03-09 Diego Paiva Pires , Kavan Modi , Lucas Chibebe Céleri

Logarithmic score and information divergence appear in information theory, statistics, statistical mechanics, and portfolio theory. We demonstrate that all these topics involve some kind of optimization that leads directly to regret…

Information Theory · Computer Science 2017-07-17 Peter Harremoës

We introduce a new concept, data irrecoverability, and show that the well-studied concept of data privacy is sufficient but not necessary for data irrecoverability. We show that there are several regularized loss minimization problems that…

Machine Learning · Computer Science 2021-07-07 Zitao Li , Jean Honorio

We present a framework to derive bounds on the test loss of randomized learning algorithms for the case of bounded loss functions. Drawing from Steinke & Zakynthinou (2020), this framework leads to bounds that depend on the conditional…

Machine Learning · Computer Science 2021-03-11 Fredrik Hellström , Giuseppe Durisi

The invariant information introduced by Brukner and Zeilinger, Phys. Rev. Lett. 83, 3354 (1999), is reconsidered from the point of view of quantum state estimation. We show that it is directly related to the mean error of the standard…

Quantum Physics · Physics 2009-11-07 J. Rehacek , Z. Hradil

The generalization error of a learning algorithm refers to the discrepancy between the loss of a learning algorithm on training data and that on unseen testing data. Various information-theoretic bounds on the generalization error have been…

Information Theory · Computer Science 2025-06-24 Xuetong Wu , Jonathan H. Manton , Uwe Aickelin , Jingge Zhu
‹ Prev 1 4 5 6 7 8 10 Next ›