English
Related papers

Related papers: Information loss from dimensionality reduction in …

200 papers

We analyze the geometry of a joint distribution over a set of discrete random variables. We briefly review Shannon's entropy, conditional entropy, mutual information and conditional mutual information. We review the entropic information…

A wide range of systems exhibit high dimensional incomplete data. Accurate estimation of the missing data is often desired, and is crucial for many downstream analyses. Many state-of-the-art recovery methods involve supervised learning…

Computer Vision and Pattern Recognition · Computer Science 2019-03-15 Adrian V. Dalca , John Guttag , Mert R. Sabuncu

We introduce a new protocol for a lossy data compression algorithm which is based on constraint satisfaction gates. We show that the theoretical capacity of algorithms built from standard parity-check gates converges exponentially fast to…

Disordered Systems and Neural Networks · Physics 2009-11-11 S. Ciliberti , M. Mezard , R. Zecchina

In this paper, some general properties of Shannon information measures are investigated over sets of probability distributions with restricted marginals. Certain optimization problems associated with these functionals are shown to be…

Information Theory · Computer Science 2020-08-13 Mladen Kovačević , Ivan Stanojević , Vojin Šenk

The concept of Shannon entropy of random variables was generalized to measurable functions in general, and to simple functions with finite values in particular. It is shown that the information measure of a function is related to the time…

Information Theory · Computer Science 2017-01-25 Guo Zhao

We investigate the local spectral statistics of the loss surface Hessians of artificial neural networks, where we discover excellent agreement with Gaussian Orthogonal Ensemble statistics across several network architectures and datasets.…

Machine Learning · Computer Science 2021-12-28 Nicholas P Baskerville , Diego Granziol , Jonathan P Keating

In the context of statistical learning, the Information Bottleneck method seeks a right balance between accuracy and generalization capability through a suitable tradeoff between compression complexity, measured by minimum description…

Information Theory · Computer Science 2021-02-16 Mohammad Mahdi Mahvari , Mari Kobayashi , Abdellatif Zaidi

We use phase space distributions specifically, the Wigner distribution (WD) and Husimi distribution (HD) to investigate certain information-theoretic measures as descriptors for a given system. We extensively investigate and analyze…

In this work, conditional entropy is used to quantify the information loss induced by passing a continuous random variable through a memoryless nonlinear input-output system. We derive an expression for the information loss depending on the…

Information Theory · Computer Science 2012-02-03 Bernhard C. Geiger , Christian Feldbauer , Gernot Kubin

Stochastic gradient descent (SGD) is a popular algorithm for optimization problems arising in high-dimensional inference tasks. Here one produces an estimator of an unknown parameter from independent samples of data by iteratively…

Machine Learning · Statistics 2023-06-23 Gerard Ben Arous , Reza Gheissari , Aukosh Jagannath

We consider Shannon entropy, Fisher information, R\'enyi entropy, and Tsallis entropy to study the quantum droplet phase in Bose-Einstein condensates. In the beyond mean-field description, the Gross-Pitaevskii equation with Lee-Huang-Yang…

Quantum Gases · Physics 2024-10-04 Sk Siddik , Golam Ali Sekh

Fabrication process variations are a major source of yield degradation in the nano-scale design of integrated circuits (IC), microelectromechanical systems (MEMS) and photonic circuits. Stochastic spectral methods are a promising technique…

Computational Engineering, Finance, and Science · Computer Science 2016-11-08 Zheng Zhang , Tsui-Wei Weng , Luca Daniel

The understanding of nonlinear, high dimensional flows, e.g, atmospheric and ocean flows, is critical to address the impacts of global climate change. Data Assimilation techniques combine physical models and observational data, often in a…

We provide a stochastic extension of the Baez-Fritz-Leinster characterization of the Shannon information loss associated with a measure-preserving function. This recovers the conditional entropy and a closely related information-theoretic…

Information Theory · Computer Science 2021-12-23 James Fullwood , Arthur J. Parzygnat

The Shannon based conditional entropy that underlies five-dimensional Einstein-Hilbert gravity coupled to a dilaton field is investigated in the context of dynamical holographic AdS/QCD models. Considering the UV and IR dominance limits of…

High Energy Physics - Theory · Physics 2016-09-22 Alex E. Bernardini , Roldao da Rocha

High-dimensional imaging is becoming increasingly relevant in many fields from astronomy and cultural heritage to systems biology. Visual exploration of such high-dimensional data is commonly facilitated by dimensionality reduction.…

Computer Vision and Pattern Recognition · Computer Science 2023-08-04 Alexander Vieth , Anna Vilanova , Boudewijn Lelieveldt , Elmar Eisemann , Thomas Höllt

In information theory, one major goal is to find useful functions that summarize the amount of information contained in the interaction of several random variables. Specifically, one can ask how the classical Shannon entropy, mutual…

Information Theory · Computer Science 2025-02-14 Leon Lang , Pierre Baudot , Rick Quax , Patrick Forré

Understanding geometric properties of natural language processing models' latent spaces allows the manipulation of these properties for improved performance on downstream tasks. One such property is the amount of data spread in a model's…

Machine Learning · Computer Science 2023-08-02 Anna C. Marbut , Katy McKinney-Bock , Travis J. Wheeler

t-SNE has gained popularity as a dimension reduction technique, especially for visualizing data. It is well-known that all dimension reduction techniques may lose important features of the data. We provide a mathematical framework for…

Machine Learning · Computer Science 2026-04-16 Rupert Li , Elchanan Mossel

In this dissertation we propose alternative analysis of distributed stochastic gradient descent (SGD) algorithms that rely on spectral properties of the data covariance. As a consequence we can relate questions pertaining to speedups and…

Optimization and Control · Mathematics 2016-09-03 Avleen S. Bijral