English
Related papers

Related papers: The information bottleneck method

200 papers

Information theory provides tools to predict the performance of a learning algorithm on a given dataset. For instance, the accuracy of learning an unknown parameter can be upper bounded by reducing the learning task to hypothesis testing…

Quantum Physics · Physics 2026-04-21 Evan Peters

We want to reconstruct a signal based on inhomogeneous data (the amount of data can vary strongly), using the model of regression with a random design. Our aim is to understand the consequences of inhomogeneity on the accuracy of estimation…

Statistics Theory · Mathematics 2016-08-16 Stéphane Gaiffas

Representation learning is an approach that allows to discover and extract the factors of variation from the data. Intuitively, a representation is said to be disentangled if it separates the different factors of variation in a way that is…

Machine Learning · Computer Science 2026-02-25 Antonio Almudévar , Alfonso Ortega

The information bottleneck problem (IB) of jointly stationary Gaussian sources is considered. A water-filling solution for the IB rate is given in terms of its SNR spectrum and whose rate is attained via frequency domain test-channel…

Information Theory · Computer Science 2022-08-23 Michael Dikshtein , Nir Weinberger , Shlomo Shamai

Demixing is the problem of identifying multiple structured signals from a superimposed, undersampled, and noisy observation. This work analyzes a general framework, based on convex optimization, for solving demixing problems. When the…

Information Theory · Computer Science 2013-10-01 Michael B. McCoy , Joel A. Tropp

The information bottleneck (IB) method is a feasible defense solution against adversarial attacks in deep learning. However, this method suffers from the spurious correlation, which leads to the limitation of its further improvement of…

Machine Learning · Computer Science 2022-10-27 Huan Hua , Jun Yan , Xi Fang , Weiquan Huang , Huilin Yin , Wancheng Ge

A new algorithm is proposed for a) unsupervised learning of sparse representations from subsampled measurements and b) estimating the parameters required for linearly reconstructing signals from the sparse codes. We verify that the new…

Neurons and Cognition · Quantitative Biology 2010-11-02 Guy Isely , Christopher J. Hillar , Friedrich T. Sommer

In discriminative settings such as regression and classification there are two random variables at play, the inputs X and the targets Y. Here, we demonstrate that the Variational Information Bottleneck can be viewed as a compromise between…

Machine Learning · Statistics 2020-11-18 Alexander A Alemi , Warren R Morningstar , Ben Poole , Ian Fischer , Joshua V Dillon

Zellner (1988) modeled statistical inference in terms of information processing and postulated the Information Conservation Principle (ICP) between the input and output of the information processing block, showing that this yielded Bayesian…

Machine Learning · Computer Science 2019-12-12 Sayandev Mukherjee

The major problem in information theoretic analysis of neural responses and other biological data is the reliable estimation of entropy--like quantities from small samples. We apply a recently introduced Bayesian entropy estimator to…

Data Analysis, Statistics and Probability · Physics 2009-09-29 Ilya Nemenman , William Bialek , Rob de Ruyter van Steveninck

Contrastive losses have been extensively used as a tool for multimodal representation learning. However, it has been empirically observed that their use is not effective to learn an aligned representation space. In this paper, we argue that…

Machine Learning · Computer Science 2025-06-06 Antonio Almudévar , José Miguel Hernández-Lobato , Sameer Khurana , Ricard Marxer , Alfonso Ortega

The goal of lossy data compression is to reduce the storage cost of a data set $X$ while retaining as much information as possible about something ($Y$) that you care about. For example, what aspects of an image $X$ contain the most…

Machine Learning · Computer Science 2020-01-16 Max Tegmark , Tailin Wu

This paper focuses on parameter estimation and introduces a new method for lower bounding the Bayesian risk. The method allows for the use of virtually \emph{any} information measure, including R\'enyi's $\alpha$, $\varphi$-Divergences, and…

Information Theory · Computer Science 2023-03-27 Amedeo Roberto Esposito , Adrien Vandenbroucque , Michael Gastpar

We address the problem of detection and estimation of one or two change-points in the mean of a series of random variables. We use the formalism of set estimation in regression: To each point of a design is attached a binary label that…

Statistics Theory · Mathematics 2018-09-07 Victor-Emmanuel Brunel

We extend the Blahut-Arimoto algorithm for maximizing Massey's directed information. The algorithm can be used for estimating the capacity of channels with delayed feedback, where the feedback is a deterministic function of the output. In…

Information Theory · Computer Science 2010-12-30 Iddo Naiss , Haim Permuter

Consider a continuous signal that cannot be observed directly. Instead, one has access to multiple corrupted versions of the signal. The available corrupted signals are correlated because they carry information about the common remote…

Information Theory · Computer Science 2016-12-06 Elaheh Mohammadi , Alireza Fallah , Farokh Marvasti

The information bottleneck principle (Shwartz-Ziv & Tishby, 2017) suggests that SGD-based training of deep neural networks results in optimally compressed hidden layers, from an information theoretic perspective. However, this claim was…

Machine Learning · Computer Science 2020-03-16 Luke Nicholas Darlow , Amos Storkey

Much of statistics relies upon four key elements: a law of large numbers, a calculus to operationalize stochastic convergence, a central limit theorem, and a framework for constructing local approximations. These elements are…

Optimization and Control · Mathematics 2018-01-09 Anil Aswani

We introduce an information theoretic measure of statistical structure, called 'binding information', for sets of random variables, and compare it with several previously proposed measures including excess entropy, Bialek et al.'s…

Statistics Theory · Mathematics 2010-12-10 Samer A. Abdallah , Mark D. Plumbley

Scientists often seek simplified representations of complex systems to facilitate prediction and understanding. If the factors comprising a representation allow us to make accurate predictions about our system, but obscuring any subset of…

Machine Learning · Computer Science 2017-10-12 Greg Ver Steeg , Rob Brekelmans , Hrayr Harutyunyan , Aram Galstyan
‹ Prev 1 8 9 10 Next ›