English
Related papers

Related papers: A partial information decomposition for discrete a…

200 papers

Personal Information Management (PIM) refers to the practice and the study of the activities a person performs in order to acquire or create, store, organize, maintain, retrieve, use, and distribute information in each of its many forms…

Human-Computer Interaction · Computer Science 2021-07-13 William Jones , Jesse David Dinneen , Robert Capra , Anne R. Diekema , Manuel A. Pérez-Quiñones

The introduction of the partial information decomposition generated a flurry of proposals for defining an intersection information that quantifies how much of "the same information" two or more random variables specify about a target random…

Information Theory · Computer Science 2015-06-11 Virgil Griffith , Edwin K. P. Chong , Ryan G. James , Christopher J. Ellison , James P. Crutchfield

Estimating mutual information from observed samples is a basic primitive, useful in several machine learning tasks including correlation mining, information bottleneck clustering, learning a Chow-Liu tree, and conditional independence…

Information Theory · Computer Science 2018-10-11 Weihao Gao , Sreeram Kannan , Sewoong Oh , Pramod Viswanath

Observations on the past provide some hints about what will happen in the future, and this can be quantified using information theory. The ``predictive information'' defined in this way has connections to measures of complexity that have…

Statistical Mechanics · Physics 2007-05-23 William Bialek , Naftali Tishby

Quantifying integrated information is a leading approach towards building a fundamental theory of consciousness. Integrated Information Theory (IIT) has gained attention in this regard due to its theoretically strong framework. However, it…

Information Theory · Computer Science 2016-12-15 Mohit Virmani , Nithin Nagaraj

Integrated Information Theory (IIT) is a prominent theory of consciousness that has at its centre measures that quantify the extent to which a system generates more information than the sum of its parts. While several candidate measures of…

Neurons and Cognition · Quantitative Biology 2019-01-30 Pedro A. M. Mediano , Anil K. Seth , Adam B. Barrett

We develop a data-driven information-theoretic framework for sharp partial identification of causal effects under unmeasured confounding. Existing approaches often rely on restrictive assumptions, such as bounded or discrete outcomes;…

Machine Learning · Statistics 2026-02-24 Yonghan Jung , Bogyeong Kang

As digital data become increasingly available for research, there is a growing awareness of the value of domain agnostic Persistent Identifiers (PIDs) for data. A PID is a globally unique reference to a digital object, which in our case is…

Digital Libraries · Computer Science 2019-07-05 Yu Luo , Beth Plale

Williams and Beer (2010) proposed a nonnegative mutual information decomposition, based on the construction of information gain lattices, which allows separating the information that a set of variables contains about another into components…

Data Analysis, Statistics and Probability · Physics 2017-04-05 Daniel Chicharro , Stefano Panzeri

Given two channels that convey information about the same random variable, we introduce two measures of the unique information of one channel with respect to the other. The two quantities are based on the notion of generalized weighted Le…

Information Theory · Computer Science 2019-12-10 Pradeep Kr. Banerjee , Eckehard Olbrich , Jürgen Jost , Johannes Rauh

Reshef et al. recently proposed a new statistical measure, the "maximal information coefficient" (MIC), for quantifying arbitrary dependencies between pairs of stochastic quantities. MIC is based on mutual information, a fundamental…

Quantitative Methods · Quantitative Biology 2015-06-12 Justin B. Kinney , Gurinder S. Atwal

Data discretization, also known as binning, is a frequently used technique in computer science, statistics, and their applications to biological data analysis. We present a new method for the discretization of real-valued data into a finite…

Other Quantitative Biology · Quantitative Biology 2007-05-23 Elena S. Dimitrova , John J. McGee , Reinhard C. Laubenbacher

Given a pair of predictor variables and a response variable, how much information do the predictors have about the response, and how is this information distributed between unique, redundant, and synergistic components? Recent work has…

Information Theory · Computer Science 2018-10-29 Pradeep Kr. Banerjee , Johannes Rauh , Guido Montúfar

When evaluating causal influence from one time series to another in a multivariate dataset it is necessary to take into account the conditioning effect of the other variables. In the presence of many variables, and possibly of a reduced…

Data Analysis, Statistics and Probability · Physics 2012-03-26 Daniele Marinazzo , Mario Pellicoro , Sebastiano Stramaglia

Many AI researchers argue that probability theory is only capable of dealing with uncertainty in situations where a full specification of a joint probability distribution is available, and conclude that it is not suitable for application in…

Artificial Intelligence · Computer Science 2013-04-05 Linda C. van der Gaag

We propose a unified theoretical framework for quantifying spatio-temporal interactions in a stochastic dynamical system based on information geometry. In the proposed framework, the degree of interactions is quantified by the divergence…

Neurons and Cognition · Quantitative Biology 2016-12-08 Masafumi Oizumi , Naotsugu Tsuchiya , Shun-ichi Amari

Information-theoretic quantities, such as entropy, are used to quantify the amount of information a given variable provides. Entropies can be used together to compute the mutual information, which quantifies the amount of information two…

Data Analysis, Statistics and Probability · Physics 2014-12-22 Kevin H. Knuth , Deniz Gençağa , William B. Rossow

Partial information decomposition has recently found applications in biological signal processing and machine learning. Despite its impacts, the decomposition was introduced through an informal and heuristic route, and its exact operational…

Information Theory · Computer Science 2025-02-18 Chao Tian , Shlomo Shamai

Reliable estimation of predictive uncertainty is crucial for machine learning applications, particularly in high-stakes scenarios where hedging against risks is essential. Despite its significance, there is no universal agreement on how to…

Machine Learning · Computer Science 2025-06-17 Kajetan Schweighofer , Lukas Aichberger , Mykyta Ielanskyi , Sepp Hochreiter

Information theoretic quantities play an important role in various settings in machine learning, including causality testing, structure inference in graphical models, time-series problems, feature selection as well as in providing privacy…

Information Theory · Computer Science 2018-10-30 Arman Rahimzamani , Himanshu Asnani , Pramod Viswanath , Sreeram Kannan