English
Related papers

Related papers: Studying the Interplay between Information Loss an…

200 papers

Missing values, widely called as \textit{sparsity} in literature, is a common characteristic of many real-world datasets. Many imputation methods have been proposed to address this problem of data incompleteness or sparsity. However, the…

Machine Learning · Computer Science 2022-07-28 Vishwas Choudhary , Binay Gupta , Anirban Chatterjee , Subhadip Paul , Kunal Banerjee , Vijay Agneeswaran

Selecting a minimal feature set that is maximally informative about a target variable is a central task in machine learning and statistics. Information theory provides a powerful framework for formulating feature selection algorithms --…

Information Theory · Computer Science 2023-05-05 Patricia Wollstadt , Sebastian Schmitt , Michael Wibral

This paper establishes a general equivalence between discrete choice and rational inattention models. Matejka and McKay (2015, AER) showed that when information costs are modelled using the Shannon entropy function, the resulting choice…

Econometrics · Economics 2017-09-27 Mogens Fosgerau , Emerson Melo , Andre de Palma , Matthew Shum

While most useful information theoretic inequalities can be deduced from the basic properties of entropy or mutual information, up to now Shannon's entropy power inequality (EPI) is an exception: Existing information theoretic proofs of the…

Information Theory · Computer Science 2016-11-17 Olivier Rioul

Exponential models of distributions are widely used in machine learning for classiffication and modelling. It is well known that they can be interpreted as maximum entropy models under empirical expectation constraints. In this work, we…

Machine Learning · Computer Science 2012-07-19 Amir Globerson , Naftali Tishby

The representations of conditional entropy and conditional mutual information are significant in explaining the unique effects among variables. While previous studies based on conditional contrastive sampling have effectively removed…

Machine Learning · Computer Science 2025-01-07 Keng Hou Leong , Yuxuan Xiu , Wai Kin , Chan

We study trade-off relations in information extraction from quantum systems subject to null-result weak measurements, where the absence of a detected photon continuously updates the system state. We present a detailed analysis of qubit and…

Quantum Physics · Physics 2026-05-15 Luis D. Zambrano Palma , Yusef Maleki , M. Suhail Zubairy

While most useful information theoretic inequalities can be deduced from the basic properties of entropy or mutual information, Shannon's entropy power inequality (EPI) seems to be an exception: available information theoretic proofs of the…

Information Theory · Computer Science 2016-11-17 Olivier Rioul

We present an information-theoretic framework for discrete diffusion models that yields principled estimators of log-likelihood using score-matching losses. Inspired by the I-MMSE identity for the Gaussian setup, we derive analogous results…

Machine Learning · Computer Science 2025-10-29 Moongyu Jeon , Sangwoo Shin , Dongjae Jeon , Albert No

Mixture proportion estimation (MPE) aims to estimate class priors from unlabeled data. This task is a critical component in weakly supervised learning, such as PU learning, learning with label noise, and domain adaptation. Existing MPE…

Machine Learning · Computer Science 2026-04-09 Yushi Hirose , Akito Narahara , Takafumi Kanamori

By filling in missing values in datasets, imputation allows these datasets to be used with algorithms that cannot handle missing values by themselves. However, missing values may in principle contribute useful information that is lost…

Machine Learning · Computer Science 2024-10-31 Oliver Urs Lenz , Daniel Peralta , Chris Cornelis

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

This paper proposes a deep representation learning using an information-theoretic loss with an aim to increase the inter-class distances as well as within-class similarity in the embedded space. Tasks such as anomaly and out-of-distribution…

Machine Learning · Computer Science 2022-02-08 Shin Ando

Semi-supervised learning (SSL) constructs classifiers using both labelled and unlabelled data. It leverages information from labelled samples, whose acquisition is often costly or labour-intensive, together with unlabelled data to enhance…

Machine Learning · Statistics 2025-12-29 Jinran Wu , You-Gan Wang , Geoffrey J. McLachlan

Information theory plays a central role in establishing fundamental limits on what any learning or estimation algorithm can -- and cannot -- achieve, regardless of computational power. In this chapter, we provide an introduction to these…

Information Theory · Computer Science 2026-05-11 Abbas El Gamal , Maxim Raginsky

We characterize information as risk reduction between knowledge states represented by partitions of the underlying probability space. Entropy corresponds to risk reduction from no (or partial) knowledge to full knowledge about a random…

Information Theory · Computer Science 2026-02-24 Sebastian Gottwald , Daniel A. Braun

Machine learning with missing data has been approached in two different ways, including feature imputation where missing feature values are estimated based on observed values, and label prediction where downstream labels are learned…

Machine Learning · Computer Science 2020-11-02 Jiaxuan You , Xiaobai Ma , Daisy Yi Ding , Mykel Kochenderfer , Jure Leskovec

We describe and develop a close relationship between two problems that have customarily been regarded as distinct: that of maximizing entropy, and that of minimizing worst-case expected loss. Using a formulation grounded in the equilibrium…

Statistics Theory · Mathematics 2007-06-13 Peter D. Grunwald , A. Philip Dawid

Contrastive representation learning, which aims to learnthe shared information between different views of unlabeled data by maximizing the mutual information between them, has shown its powerful competence in self-supervised learning for…

Machine Learning · Computer Science 2024-08-21 Xuechu Yu

Neural networks achieve remarkable performance through superposition: encoding multiple features as overlapping directions in activation space rather than dedicating individual neurons to each feature. This challenges interpretability, yet…

Machine Learning · Computer Science 2025-12-16 Leonard Bereska , Zoe Tzifa-Kratira , Reza Samavi , Efstratios Gavves