English
Related papers

Related papers: Variational Information Maximisation for Intrinsic…

200 papers

In many applications, it is desirable to extract only the relevant information from complex input data, which involves making a decision about which input features are relevant. The information bottleneck method formalizes this as an…

Machine Learning · Statistics 2020-04-28 Anirudh Goyal , Yoshua Bengio , Matthew Botvinick , Sergey Levine

In this paper, we revisit variational intrinsic control (VIC), an unsupervised reinforcement learning method for finding the largest set of intrinsic options available to an agent. In the original work by Gregor et al. (2016), two VIC…

Machine Learning · Computer Science 2021-03-18 Taehwan Kwon

One of the fundamental steps toward understanding a complex system is identifying variation at the scale of the system's components that is most relevant to behavior on a macroscopic scale. Mutual information provides a natural means of…

Machine Learning · Computer Science 2024-03-20 Kieran A. Murphy , Dani S. Bassett

End-to-end deep learning for communication systems, i.e., systems whose encoder and decoder are learned, has attracted significant interest recently, due to its performance which comes close to well-developed classical encoder-decoder…

Information Theory · Computer Science 2019-03-12 Rick Fritschek , Rafael F. Schaefer , Gerhard Wunder

We formulate and analyze the compound information bottleneck programming. In this problem, a Markov chain $ \mathsf{X} \rightarrow \mathsf{Y} \rightarrow \mathsf{Z} $ is assumed with fixed marginal distributions $\mathsf{P}_{\mathsf{X}}$…

Information Theory · Computer Science 2022-05-11 Michael Dikshtein , Nir Weinberger , Shlomo Shamai

Evaluating large language models across many benchmarks is expensive, yet many benchmarks are highly correlated. We formalize the selection of a small, informative subset as submodular maximization under a multivariate Gaussian model.…

Artificial Intelligence · Computer Science 2026-05-05 Alexander Smola

Empowerment, an information-theoretic measure of an agent's potential influence on its environment, has emerged as a powerful intrinsic motivation and exploration framework for reinforcement learning (RL). Besides for unsupervised RL and…

Artificial Intelligence · Computer Science 2025-10-08 Moritz Schneider , Robert Krug , Narunas Vaskevicius , Luigi Palmieri , Michael Volpp , Joschka Boedecker

Many real-world tasks require optimizing expensive black-box functions accessible only through noisy evaluations, a setting commonly addressed with Bayesian optimization (BO). While Bayesian neural networks (BNNs) have recently emerged as…

Machine Learning · Computer Science 2026-01-14 Farhad Mirkarimi

Information theoretic measures (entropies, entropy rates, mutual information) are nowadays commonly used in statistical signal processing for real-world data analysis. The present work proposes the use of Auto Mutual Information (Mutual…

Data Analysis, Statistics and Probability · Physics 2019-07-24 C Granero-Belinchón , S. Roux , P. Abry , N. Garnier

Our understanding of complex systems rests on our ability to characterise how they perform distributed computation and integrate information. Advances in information theory have introduced several quantities to describe complex information…

Information Theory · Computer Science 2026-04-13 Alberto Liardi , George Blackburne , Hardik Rajpal , Fernando E. Rosas , Pedro A. M. Mediano

Model-based reinforcement learning methods learn a dynamics model with real data sampled from the environment and leverage it to generate simulated data to derive an agent. However, due to the potential distribution mismatch between…

Machine Learning · Computer Science 2020-10-29 Jian Shen , Han Zhao , Weinan Zhang , Yong Yu

This paper presents expression of mutual information that defines the information gain in planning of sensing resources, when the goal is to reduce the forecast uncertainty of some quantities of interest and the system dynamics is described…

Systems and Control · Computer Science 2013-08-02 Han-Lim Choi

This work focuses on learning useful and robust deep world models using multiple, possibly unreliable, sensors. We find that current methods do not sufficiently encourage a shared representation between modalities; this can cause poor…

Machine Learning · Computer Science 2021-07-07 Kaiqi Chen , Yong Lee , Harold Soh

The information bottleneck principle is an elegant and useful approach to representation learning. In this paper, we investigate the problem of representation learning in the context of reinforcement learning using the information…

Machine Learning · Computer Science 2019-11-14 Pei Yingjun , Hou Xinwen

In this contribution, an algorithm for evaluating the capacity-achieving input covariance matrices for frequency selective Rayleigh MIMO channels is proposed. In contrast with the flat fading Rayleigh case, no closed-form expressions for…

Information Theory · Computer Science 2011-04-13 Florian Dupuy , Philippe Loubaton

This paper recalls the proximal point method. We study two iterative algorithms: the Blahut-Arimoto algorithm for computing the capacity of arbitrary discrete memoryless channels, as an example of an iterative algorithm working with…

Information Theory · Computer Science 2010-01-13 Ziad Naja , Florence Alberge , P. Duhamel

In this paper we study consensus-based optimization (CBO), a versatile, flexible and customizable optimization method suitable for performing nonconvex and nonsmooth global optimizations in high dimensions. CBO is a multi-particle…

Numerical Analysis · Mathematics 2026-05-28 Konstantin Riedl

Overfitting data is a well-known phenomenon related with the generation of a model that mimics too closely (or exactly) a particular instance of data, and may therefore fail to predict future observations reliably. In practice, this…

Machine Learning · Statistics 2023-04-14 Matias Vera , Leonardo Rey Vega , Pablo Piantanida

A fundamental challenge in reinforcement learning is to learn policies that generalize beyond the operating domains experienced during training. In this paper, we approach this challenge through the following invariance principle: an agent…

Machine Learning · Computer Science 2020-11-10 Anoopkumar Sonar , Vincent Pacelli , Anirudha Majumdar

Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental…

Artificial Intelligence · Computer Science 2016-06-01 Guido Montufar , Keyan Ghazi-Zahedi , Nihat Ay