English
Related papers

Related papers: Information loss from dimensionality reduction in …

200 papers

The problem of finding a reduced dimensionality representation of categorical variables while preserving their most relevant characteristics is fundamental for the analysis of complex data. Specifically, given a co-occurrence matrix of two…

Machine Learning · Computer Science 2012-12-12 Amir Globerson , Gal Chechik , Naftali Tishby

We consider the problem of reducing the dimensions of parameters and data in non-Gaussian Bayesian inference problems. Our goal is to identify an "informed" subspace of the parameters and an "informative" subspace of the data so that a…

Computation · Statistics 2022-07-19 Ricardo Baptista , Youssef Marzouk , Olivier Zahm

We introduce the notion of relevant information loss for the purpose of casting the signal enhancement problem in information-theoretic terms. We show that many algorithms from machine learning can be reformulated using relevant information…

Information Theory · Computer Science 2013-12-20 Bernhard C. Geiger , Gernot Kubin

Loss Given Default (LGD) modeling faces a fundamental data quality constraint: 90% of available training data consists of proxy estimates based on pre-distress balance sheets rather than actual recovery outcomes from completed bankruptcy…

Machine Learning · Computer Science 2025-11-18 Javier Marín

Computing expected information gain (EIG) from prior to posterior (equivalently, mutual information between candidate observations and model parameters or other quantities of interest) is a fundamental challenge in Bayesian optimal…

Methodology · Statistics 2026-01-30 Fengyi Li , Ricardo Baptista , Youssef Marzouk

We initiate the study of differentially private (DP) estimation with access to a small amount of public data. For private estimation of d-dimensional Gaussians, we assume that the public data comes from a Gaussian that may have vanishing…

Machine Learning · Computer Science 2023-04-07 Alex Bie , Gautam Kamath , Vikrant Singhal

Complementarity relations between various characterizations of a probability distribution are at the core of information theory. In particular, lower and upper bounds for the entropic function are of great importance. In applied topics, we…

Quantum Physics · Physics 2022-09-07 Alexey E. Rastegin

Shannon's information entropy measures of the uncertainty of an event's outcome. If learning about a system reflects a decrease in uncertainty, then a plausible intuition is that learning should be accompanied by a decrease in the entropy…

Robotics · Computer Science 2015-02-20 Paul E. Smaldino

We deploy Shannon's information entropy to the distribution of branching fractions in a particle decay. This serves to quantify how important a given new reported decay channel is, from the point of view of the information that it adds to…

The amount of information lost in sub-Nyquist sampling of a continuous-time Gaussian stationary process is quantified. We consider a combined source coding and sub-Nyquist reconstruction problem in which the input to the encoder is a noisy…

Information Theory · Computer Science 2016-01-26 Alon Kipnis , Andrea J. Goldsmith , Yonina C. Eldar , Tsachy Weissman

This paper studies the problem of estimating the differential entropy $h(S+Z)$, where $S$ and $Z$ are independent $d$-dimensional random variables with $Z\sim\mathcal{N}(0,\sigma^2 \mathrm{I}_d)$. The distribution of $S$ is unknown, but $n$…

Statistics Theory · Mathematics 2019-06-04 Ziv Goldfeld , Kristjan Greenewald , Yury Polyanskiy

We generalize the Point information gain (PIG) and derived quantities, i.e. Point information entropy (PIE) and Point information entropy density (PIED), for the case of R\'enyi entropy and simulate the behavior of PIG for typical…

Data Analysis, Statistics and Probability · Physics 2016-10-21 Renata Rychtáriková , Jan Korbel , Petr Macháček , Petr Císař , Jan Urban , Dmytro Soloviov , Dalibor Štys

A simple, intuitive approach to the assessment of probabilistic inferences is introduced. The Shannon information metrics are translated to the probability domain. The translation shows that the negative logarithmic score and the geometric…

Other Statistics · Statistics 2018-12-27 Kenric P. Nelson

In a previous paper (C. Cafaro et al., 2012), we compared an uncorrelated 3D Gaussian statistical model to an uncorrelated 2D Gaussian statistical model obtained from the former model by introducing a constraint that resembles the quantum…

Chaotic Dynamics · Physics 2015-06-17 Adom Giffin , S. A. Ali , Carlo Cafaro

Information theory is an excellent framework for analyzing Earth system data because it allows us to characterize uncertainty and redundancy, and is universally interpretable. However, accurately estimating information content is…

Applications · Statistics 2024-10-30 J. Emmanuel Johnson , Valero Laparra , Maria Piles , Gustau Camps-Valls

This paper considers the subject of information losses arising from the finite datasets used in the training of neural classifiers. It proves a relationship between such losses as the product of the expected total variation of the estimated…

Machine Learning · Computer Science 2020-01-09 Brandon Foggo , Nanpeng Yu , Jie Shi , Yuanqi Gao

The amount of information available in spectro-polarimetric data is estimated. To this end, the intrinsic dimensionality of the data is inferred with the aid of a recently derived estimator based on nearest-neighbor considerations and…

Information theoretical measures, such as entropy, mutual information, and various divergences, exhibit robust characteristics in image registration applications. However, the estimation of these quantities is computationally intensive in…

Information Theory · Computer Science 2012-10-03 Zoltan Szabo , Andras Lorincz

Bayesian optimal experimental design provides a principled framework for selecting experimental settings that maximize obtained information. In this work, we focus on estimating the expected information gain in the setting where the…

Machine Learning · Statistics 2025-10-02 Chuntao Chen , Tapio Helin , Nuutti Hyvönen , Yuya Suzuki

spectral-based subspace learning is a common data preprocessing step in many machine learning pipelines. The main aim is to learn a meaningful low dimensional embedding of the data. However, most subspace learning methods do not take into…

Machine Learning · Computer Science 2023-06-14 Firas Laakom , Jenni Raitoharju , Nikolaos Passalis , Alexandros Iosifidis , Moncef Gabbouj