English
Related papers

Related papers: Optimal information deletion and Bayes' theorem

200 papers

Information divergence that measures the difference between two nonnegative matrices or tensors has found its use in a variety of machine learning problems. Examples are Nonnegative Matrix/Tensor Factorization, Stochastic Neighbor…

Machine Learning · Computer Science 2014-06-06 Onur Dikmen , Zhirong Yang , Erkki Oja

One of the benefits of belief networks and influence diagrams is that so much knowledge is captured in the graphical structure. In particular, statements of conditional irrelevance (or independence) can be verified in time linear in the…

Artificial Intelligence · Computer Science 2013-02-01 Ross D. Shachter

We propose a new model selection method, the posterior averaging information criterion, for Bayesian model assessment from a predictive perspective. The theoretical foundation is built on the Kullback-Leibler divergence to quantify the…

Methodology · Statistics 2020-09-22 Shouhao Zhou

Within the Kolmogorov theory of probability, Bayes' rule allows one to perform statistical inference by relating conditional probabilities to unconditional probabilities. As we show here, however, there is a continuous set of alternative…

Probability · Mathematics 2014-12-05 Samuel G. Rodriques

In this paper we propose a Bayesian, information theoretic approach to dimensionality reduction. The approach is formulated as a variational principle on mutual information, and seamlessly addresses the notions of sufficiency, relevance,…

Data Analysis, Statistics and Probability · Physics 2007-05-23 David R. Wolf , Edward I. George

In a given problem, the Bayesian statistical paradigm requires the specification of a prior distribution that quantifies relevant information about the unknowns of main interest external to the data. In cases where little such information…

Statistics Theory · Mathematics 2017-10-11 Alexander Terenin , David Draper

We present a Bayesian sequential decision-making formulation of the information filtering problem, in which an algorithm presents items (news articles, scientific papers, tweets) arriving in a stream, and learns relevance from user feedback…

Machine Learning · Computer Science 2016-10-25 Bangrui Chen , Peter I. Frazier

We consider information filtering, in which we face a stream of items too voluminous to process by hand (e.g., scientific articles, blog posts, emails), and must rely on a computer system to automatically filter out irrelevant items. Such…

Optimization and Control · Mathematics 2015-02-10 Xiaoting Zhao , Peter I. Frazier

In this paper we formulate the problem of inference under incomplete information in very general terms. This includes modelling the process responsible for the incompleteness, which we call the incompleteness process. We allow the process…

Artificial Intelligence · Computer Science 2014-01-16 Marco Zaffalon , Enrique Miranda

This work investigates the information loss in a decimation system, i.e., in a downsampler preceded by an anti-aliasing filter. It is shown that, without a specific signal model in mind, the anti-aliasing filter cannot reduce information…

Information Theory · Computer Science 2014-07-08 Bernhard C. Geiger , Gernot Kubin

Partial Information Decomposition (PID) seeks to disentangle how information about a target variable is distributed across multiple sources, separating redundant, unique, and synergistic contributions. Despite extensive theoretical…

Information Theory · Computer Science 2025-12-19 Philip Hendrik Matthias , Abdullah Makkeh , Michael Wibral , Aaron J. Gutknecht

We investigate the problem of estimating the causal effect of a treatment on individual subjects from observational data, this is a central problem in various application domains, including healthcare, social sciences, and online…

Methodology · Statistics 2019-01-30 Ahmed M. Alaa , Mihaela van der Schaar

Selecting an optimal subset of features or instances under an information theoretic criterion has become an effective preprocessing strategy for reducing data complexity while preserving essential information. This study investigates two…

Optimization and Control · Mathematics 2025-08-25 Taotao He , Jun Luo , Junkai Zhao

This paper presents a new foundational approach to information theory based on the concept of the information efficiency of a recursive function, which is defined as the difference between the information in the input and the output. The…

Information Theory · Computer Science 2023-08-29 Pieter Adriaans

The problem of source separation is by its very nature an inductive inference problem. There is not enough information to deduce the solution, so one must use any available information to infer the most probable solution. We demonstrate…

Data Analysis, Statistics and Probability · Physics 2007-05-23 Kevin H. Knuth

The information describing the conditions of a system or a person is constantly evolving and may become obsolete and contradict other information. A database, therefore, must be consistently updated upon the acquisition of new valid…

Artificial Intelligence · Computer Science 2022-05-05 Salma Chaieb , Brahim Hnich , Ali Ben Mrad

Following the critical review of Seaman et al. (2012), we reflect on what is presumably the most essential aspect of Bayesian statistics, namely the selection of a prior density. In some cases, Bayesian inference remains fairly stable under…

Methodology · Statistics 2014-07-23 Kaniav Kamary , Christian P. Robert

In this paper, we extend the transfer learning classification framework from regression function-based methods to decision rules. We propose a novel methodology for modeling posterior drift through Bayes decision rules. By exploiting the…

Machine Learning · Statistics 2025-08-29 Xiaohan Wang , Yang Ning

The Principle of Maximum Entropy is a rigorous technique for estimating an unknown distribution given partial information while simultaneously minimizing bias. However, an important requirement for applying the principle is that the…

Information Theory · Computer Science 2026-02-03 Kenneth Bogert , Matthew Kothe

Given the joint chances of a pair of random variables one can compute quantities of interest, like the mutual information. The Bayesian treatment of unknown chances involves computing, from a second order prior distribution and the data…

Machine Learning · Computer Science 2007-05-23 Marcus Hutter , Marco Zaffalon