English
Related papers

Related papers: Innovation Capacity of Dynamical Learning Systems

200 papers

The cognitive interference channel (C-IFC) consists of a classical two-user interference channel in which the message of one user (the "primary" user) is non-causally available at the transmitter of the other user (the "cognitive" user). We…

Information Theory · Computer Science 2016-11-18 Stefano Rini , Daniela Tuninetti , Natasha Devroye

This work presents a complete geometrical characterisation of divisible and indivisible time-evolution at the level of probabilities for systems with two configurations, open or closed. Our new geometrical construction in the space of…

Quantum Physics · Physics 2025-05-14 Leandro Silva Pimenta

Common information (CI) is ubiquitous in information theory and related areas such as theoretical computer science and discrete probability. However, because there are multiple notions of CI, a unified understanding of the deep…

Information Theory · Computer Science 2022-11-04 Lei Yu , Vincent Y. F. Tan

We study the information transmission capacities of quantum Markov semigroups $(\Psi^t)_{t\in \mathbb{N}}$ acting on $d-$dimensional quantum systems. We show that, in the limit of $t\to \infty$, the capacities can be efficiently computed in…

Quantum Physics · Physics 2026-04-22 Satvik Singh , Nilanjana Datta

Variational dimensionality reduction methods are widely used for their accuracy, generative capabilities, and robustness. We introduce a unifying framework that generalizes both such as traditional and state-of-the-art methods. The…

Machine Learning · Computer Science 2025-09-04 Eslam Abdelaleem , Ilya Nemenman , K. Michael Martini

The information bottleneck framework provides a systematic approach to learning representations that compress nuisance information in the input and extract semantically meaningful information about predictions. However, the choice of a…

The rising computational and energy demands of artificial intelligence systems urge the exploration of alternative software and hardware solutions that exploit physical effects for computation. According to machine learning theory, a neural…

Chaotic Dynamics · Physics 2025-04-11 Hend Abdel-Ghani , A. H. Abbas , Ivan S. Maksymov

Intelligent systems must deploy internal representations that are simultaneously structured -- to support broad generalization -- and selective -- to preserve input identity. We expose a fundamental limit on this tradeoff. For any model…

Computable Information Density (CID), the ratio of the length of a losslessly compressed data file to that of the uncompressed file, is a measure of order and correlation in both equilibrium and nonequilibrium systems. Here we show that…

Statistical Mechanics · Physics 2020-10-26 Stefano Martiniani , Yuval Lemberg , Paul M. Chaikin , Dov Levine

We present new results to model and understand the role of encoder-decoder design in machine learning (ML) from an information-theoretic angle. We use two main information concepts, information sufficiency (IS) and mutual information loss…

Machine Learning · Computer Science 2024-06-03 Jorge F. Silva , Victor Faraggi , Camilo Ramirez , Alvaro Egana , Eduardo Pavez

In problem-solving, we humans can come up with multiple novel solutions to the same problem. However, reinforcement learning algorithms can only produce a set of monotonous policies that maximize the cumulative reward but lack diversity and…

Machine Learning · Computer Science 2022-11-01 Hao Sun , Zhenghao Peng , Bo Dai , Jian Guo , Dahua Lin , Bolei Zhou

The realization of complex classification tasks requires training of deep learning (DL) architectures consisting of tens or even hundreds of convolutional and fully connected hidden layers, which is far from the reality of the human brain.…

Machine Learning · Computer Science 2023-04-21 Yuval Meir , Ofek Tevet , Yarden Tzach , Shiri Hodassman , Ronit D. Gross , Ido Kanter

A major challenge in designing efficient statistical supervised learning algorithms is finding representations that perform well not only on available training samples but also on unseen data. While the study of representation learning has…

Machine Learning · Statistics 2024-02-06 Milad Sefidgaran , Abdellatif Zaidi , Piotr Krasnowski

The Information Bottleneck (IB) principle facilitates effective representation learning by preserving label-relevant information while compressing irrelevant information. However, its strong reliance on accurate labels makes it inherently…

Machine Learning · Computer Science 2025-12-12 Yi Huang , Qingyun Sun , Yisen Gao , Haonan Yuan , Xingcheng Fu , Jianxin Li

We introduce a novel, biologically plausible local learning rule that provably increases the robustness of neural dynamics to noise in nonlinear recurrent neural networks with homogeneous nonlinearities. Our learning rule achieves higher…

Neurons and Cognition · Quantitative Biology 2022-10-12 Christopher H. Stock , Sarah E. Harvey , Samuel A. Ocko , Surya Ganguli

This paper proposes an information-theoretic representation learning framework, named conditional information flow maximization, to extract noise-invariant sufficient representations for the input data and target task. It promotes the…

Machine Learning · Computer Science 2024-08-13 Dou Hu , Lingwei Wei , Wei Zhou , Songlin Hu

Measurements acquired from distributed physical systems are often sparse and noisy. Therefore, signal processing and system identification tools are required to mitigate noise effects and reconstruct unobserved dynamics from limited sensor…

Machine Learning · Computer Science 2025-09-08 Omid Sedehi , Manish Yadav , Merten Stender , Sebastian Oberst

We develop a deterministic large-time mechanism yielding Ces{\`a}ro asymptotic observability inequalities from moving localized observations for conservative evolutions. On each observation interval, exact convexification on a compact…

Analysis of PDEs · Mathematics 2026-05-13 Maarten V. de Hoop , Antti Kykkänen , Emmanuel Trélat

Storage-efficient privacy-preserving learning is crucial due to increasing amounts of sensitive user data required for modern learning tasks. We propose a framework for reducing the storage cost of user data while at the same time providing…

Information Theory · Computer Science 2023-03-23 Berivan Isik , Tsachy Weissman

We employ a unified framework for computing the information capacity of biological signaling systems using Fisher Information. By deriving closed-form or easily computable information capacity formulas, we quantify how well different…

Quantitative Methods · Quantitative Biology 2025-05-14 Michał Komorowski