English
Related papers

Related papers: Mutual Information Surprise: Rethinking Unexpected…

200 papers

The amount of information exchanged per unit of time between two nodes in a dynamical network or between two data sets is a powerful concept for analysing complex systems. This quantity, known as the mutual information rate (MIR), is…

Chaotic Dynamics · Physics 2015-05-27 M. S. Baptista , R. M. Rubinger , E. R. V. Junior , J. C. Sartorelli , U. Parlitz , C. Grebogi

Multi-agent systems (MASs) can autonomously learn to solve previously unknown tasks by means of each agent's individual intelligence as well as by collaborating and exploiting collective intelligence. This article considers a group of…

Systems and Control · Electrical Eng. & Systems 2021-11-29 Michael Meindl , Fabio Molinari , Dustin Lehmann , Thomas Seel

We show that reinforcement learning agents that learn by surprise (surprisal) get stuck at abrupt environmental transition boundaries because these transitions are difficult to learn. We propose a counter-intuitive solution that we call…

Machine Learning · Computer Science 2020-01-17 Haitao Xu , Brendan McCane , Lech Szymanski , Craig Atkinson

In many complex systems, we observe that `interesting behaviour' is often the consequence of a system exploiting the existence of an Information Bottleneck (IB). These bottlenecks can occur at different scales, between individuals or…

Physics and Society · Physics 2023-08-02 Michael Crosscombe , Hiroki Sato

Mutual information (MI) is a fundamental measure of statistical dependence, with a myriad of applications to information theory, statistics, and machine learning. While it possesses many desirable structural properties, the estimation of…

Information Theory · Computer Science 2021-10-19 Ziv Goldfeld , Kristjan Greenewald

Consensus formation is pivotal in multi-agent systems (MAS), balancing collective coherence with individual diversity. Conventional LLM-based MAS primarily rely on explicit coordination, e.g., prompts or voting, risking premature…

Multiagent Systems · Computer Science 2025-05-20 Zengqing Wu , Takayuki Ito

Contrastive learning has emerged as a cornerstone in recent achievements of unsupervised representation learning. Its primary paradigm involves an instance discrimination task with a mutual information loss. The loss is known as InfoNCE and…

Artificial Intelligence · Computer Science 2023-08-31 Kyungeun Lee , Jaeill Kim , Suhyun Kang , Wonjong Rhee

A new expression as a certain asymptotic limit via "discrete micro-states" of permutations is provided to the mutual information of both continuous and discrete random variables.

Probability · Mathematics 2007-05-23 F. Hiai , D. Petz

Estimating mutual information accurately is pivotal across diverse applications, from machine learning to communications and biology, enabling us to gain insights into the inner mechanisms of complex systems. Yet, dealing with…

Machine Learning · Computer Science 2024-11-12 Nunzio A. Letizia , Nicola Novello , Andrea M. Tonello

Bayesian methods are critical for quantifying the behaviors of systems. They capture our uncertainty about a system's behavior using probability distributions and update this understanding as new information becomes available. Probabilistic…

Computation · Statistics 2018-04-25 Thomas A. Catanach , James L. Beck

Sliced Mutual Information (SMI) is widely used as a scalable alternative to mutual information for measuring non-linear statistical dependence. Despite its advantages, such as faster convergence, robustness to high dimensionality, and…

Machine Learning · Computer Science 2025-12-10 Alexander Semenenko , Ivan Butakov , Alexey Frolov , Ivan Oseledets

Reconfigurable intelligent surface (RIS) has entered the public consciousness as a promising technology for enhancing the performance of future wireless communication systems by dynamically constructing the wireless channels. In this…

Information Theory · Computer Science 2023-03-02 Pingping Zhang , Shiqi Gong , Shaodan Ma

We investigate thermodynamics of feedback processes driven by measurement. Regarding system and memory device as a composite system, mutual information as a measure of correlation between the two constituents contributes to the entropy of…

Statistical Mechanics · Physics 2017-04-12 Chulan Kwon

Mutual Information between agent Actions and environment States (MIAS) quantifies the influence of agent on its environment. Recently, it was found that the maximization of MIAS can be used as an intrinsic motivation for artificial agents.…

Machine Learning · Computer Science 2020-08-04 Ruihan Zhao , Stas Tiomkin , Pieter Abbeel

The 1st edition of the workshop on Mixed-Initiative ConveRsatiOnal Systems (MICROS@ECIR2021) aims at investigating and collecting novel ideas and contributions in the field of conversational systems. Oftentimes, the users fulfill their…

Information Retrieval · Computer Science 2021-01-26 Ida Mele , Cristina Ioana Muntean , Mohammad Aliannejadi , Nikos Voskarides

A game is introduced to study the effect of privacy in strategic communication between well-informed senders and a receiver. The receiver wants to accurately estimate a random variable. The sender, however, wants to communicate a message…

Computer Science and Game Theory · Computer Science 2015-09-21 Farhad Farokhi , Girish Nair

Among Monte Carlo techniques, the importance sampling requires fine tuning of a proposal distribution, which is now fluently resolved through iterative schemes. The Adaptive Multiple Importance Sampling (AMIS) of Cornuet et al. (2012)…

Computation · Statistics 2014-05-27 Jean-Michel Marin , Pierre Pudlo , Mohammed Sedki

Optimizing recommender systems based on user interaction data is mainly seen as a problem of dealing with selection bias, where most existing work assumes that interactions from different users are independent. However, it has been shown…

Information Retrieval · Computer Science 2022-07-04 Norman Knyazev , Harrie Oosterhuis

Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an over-reliance on replicating expert actions induces…

Robotics · Computer Science 2022-11-08 Hanbit Oh , Hikaru Sasaki , Brendan Michael , Takamitsu Matsubara

Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts to remove this constraint by defining an intrinsic reward…

Machine Learning · Computer Science 2021-03-16 Rui Zhao , Yang Gao , Pieter Abbeel , Volker Tresp , Wei Xu
‹ Prev 1 4 5 6 7 8 10 Next ›