English
Related papers

Related papers: Information-theoretic Limits of Learning and Estim…

200 papers

The presence of symmetries imposes a stringent set of constraints on a system. This constrained structure allows intelligent agents interacting with such a system to drastically improve the efficiency of learning and generalization, through…

Information Theory · Computer Science 2024-10-03 Hippolyte Charvin , Nicola Catenacci Volpi , Daniel Polani

During the last two decades, concentration of measure has been a subject of various exciting developments in convex geometry, functional analysis, statistical physics, high-dimensional statistics, probability theory, information theory,…

Information Theory · Computer Science 2015-10-13 Maxim Raginsky , Igal Sason

The principle of maximum entropy is a broadly applicable technique for computing a distribution with the least amount of information possible constrained to match empirical data, for instance, feature expectations. We seek to generalize…

Information Theory · Computer Science 2022-05-30 Kenneth Bogert

Information theory plays an indispensable role in the development of algorithm-independent impossibility results, both for communication problems and for seemingly distinct areas such as statistics and machine learning. While numerous…

Information Theory · Computer Science 2019-11-26 Jonathan Scarlett , Volkan Cevher

In this paper, a mathematical theory of learning is proposed that has many parallels with information theory. We consider Vapnik's General Setting of Learning in which the learning process is defined to be the act of selecting a hypothesis…

Machine Learning · Computer Science 2014-05-08 Ibrahim Alabdulmohsin

A new finite form of de Finetti's representation theorem is established using elementary information-theoretic tools. The distribution of the first $k$ random variables in an exchangeable vector of $n\geq k$ random variables is close to a…

Information Theory · Computer Science 2024-04-29 Mario Berta , Lampros Gavalakis , Ioannis Kontoyiannis

In this paper we formalize the notions of information elements and information lattices, first proposed by Shannon. Exploiting this formalization, we identify a comprehensive parallelism between information lattices and subgroup lattices.…

Information Theory · Computer Science 2007-10-08 Hua Li , Edwin K. P. Chong

In context-specific applications such as robotics, telecommunications, and healthcare, artificial intelligence systems often face the challenge of limited training data. This scarcity introduces epistemic uncertainty, i.e., reducible…

Information Theory · Computer Science 2026-03-17 Osvaldo Simeone , Yaniv Romano

The purpose of this paper is to formalize the concept that best synthesizes our intuitive understanding of quantum mechanics -- that the information carried by a system is limited -- and, from this principle, to construct the foundations of…

Quantum Physics · Physics 2025-07-04 Paolo Ferro

This monograph presents a unified treatment of single- and multi-user problems in Shannon's information theory where we depart from the requirement that the error probability decays asymptotically in the blocklength. Instead, the error…

Information Theory · Computer Science 2015-04-13 Vincent Y. F. Tan

A unified combinatorial definition of the information content and entropy of different types of patterns, compatible with the traditional concepts of information and entropy, going beyond the limitations of Shannon information interpretable…

Information Theory · Computer Science 2025-01-22 Zsolt Pocze

We present a unifying picture of PAC-Bayesian and mutual information-based upper bounds on the generalization error of randomized learning algorithms. As we show, Tong Zhang's information exponential inequality (IEI) gives a general recipe…

Machine Learning · Computer Science 2021-10-26 Pradeep Kr. Banerjee , Guido Montúfar

Information theory is a practical and theoretical framework developed for the study of communication over noisy channels. Its probabilistic basis and capacity to relate statistical structure to function make it ideally suited for studying…

Neurons and Cognition · Quantitative Biology 2015-01-09 Robin A. A. Ince , Simon R. Schultz , Stefano Panzeri

A crucial assumption underlying the most current theory of machine learning is that the training distribution is identical to the test distribution. However, this assumption may not hold in some real-world applications. In this paper, we…

Machine Learning · Statistics 2023-02-24 Jiangshe Zhang , Lizhen Ji , Fei Gao , Mengyao Li

In this paper, we establish generalization bounds for transductive learning algorithms in the context of information theory and PAC-Bayes, covering both the random sampling and the random splitting setting. First, we show that the…

Machine Learning · Computer Science 2025-01-22 Huayi Tang , Yong Liu

A unified thermodynamic formalism describing the efficiency of learning is proposed. First, we derive an inequality, which is more strength than Clausius's inequality, revealing the lower bound of the entropy-production rate of a subsystem.…

Statistical Mechanics · Physics 2025-04-15 Shanhe Su , Ousi Pan , Shihao Xia , Jincan Chen , Chikako Uchiyama

The concept of autonomy is fundamental for understanding biological organization and the evolutionary transitions of living systems. Understanding how a system constitutes itself as an individual, cohesive, self-organized entity is a…

Neurons and Cognition · Quantitative Biology 2019-02-07 Miguel Aguilera , Ezequiel Di Paolo

Two main concepts studied in machine learning theory are generalization gap (difference between train and test error) and excess risk (difference between test error and the minimum possible error). While information-theoretic tools have…

Machine Learning · Computer Science 2023-03-01 Hassan Hafez-Kolahi , Behrad Moniri , Shohreh Kasaei

We identify fundamental issues with discretization when estimating information-theoretic quantities in the analysis of data. These difficulties are theoretical in nature and arise with discrete datasets carrying significant implications for…

Quantitative Methods · Quantitative Biology 2014-06-24 Venkateshan Kannan , Jesper Tegnèr

In order to find out the limiting speed of solving a specific problem using computer, this essay provides a method based on information entropy. The relationship between the minimum computational complexity and information entropy change is…

Computational Complexity · Computer Science 2012-03-09 Xue Wu