English
Related papers

Related papers: Geometric Brownian Information Engine: Essentials …

200 papers

Information Bottleneck (IB) is widely used, but in deep learning, it is usually implemented through tractable surrogates, such as variational bounds or neural mutual information (MI) estimators, rather than directly controlling the MI…

Machine Learning · Computer Science 2026-02-05 Weiqi Wang , Zhiyi Tian , Chenhan Zhang , Shui Yu

We study a two-level system controlled in a discrete feedback loop, modeling both the system and the controller in terms of stochastic Markov processes. We find that the extracted work, which is known to be bounded from above by the mutual…

Statistical Mechanics · Physics 2015-09-02 Jaegon Um , Haye Hinrichsen , Chulan Kwon , Hyunggyu Park

The key factor currently limiting the advancement of computational power of electronic computation is no longer the manufacturing density and speed of components, but rather their high energy consumption. While it has been widely argued…

Data Structures and Algorithms · Computer Science 2024-08-30 David Doty , Niels Kornerup , Austin Luchsinger , Leo Orshansky , David Soloveichik , Damien Woods

Brownian escape is key to a wealth of physico-chemical processes, including polymer folding, and information storage. The frequency of thermally activated energy barrier crossings is assumed to generally decrease exponentially with…

Soft Condensed Matter · Physics 2020-06-19 Marie Chupeau , Jannes Gladrow , Alexei Chepelianskii , Ulrich F. Keyser , Emmanuel Trizac

Gaussian process (GP) regression is a Bayesian nonparametric method for regression and interpolation, offering a principled way of quantifying the uncertainties of predicted function values. For the quantified uncertainties to be…

Statistics Theory · Mathematics 2025-08-22 Masha Naslidnyk , Motonobu Kanagawa , Toni Karvonen , Maren Mahsereci

Information can improve heat engine performance, but the underlying principles are still not so clear. Here we introduce a Carnot information machine (CIE) and obtain a quantitative relationship between the engine performance and…

Statistical Mechanics · Physics 2025-07-21 Yang Xiao , Qian Zeng , Jin Wang

One of the well-known challenges in optimal experimental design is how to efficiently estimate the nested integrations of the expected information gain. The Gaussian approximation and associated importance sampling have been shown to be…

Computation · Statistics 2021-08-17 Quan Long

A genuine feature of projective quantum measurements is that they inevitably alter the mean energy of the observed system if the measured quantity does not commute with the Hamiltonian. Compared to the classical case, Jacobs proved that…

Statistical Mechanics · Physics 2015-06-10 Kay Brandner , Michael Bauer , Michael T. Schmid , Udo Seifert

Information theoretic active learning has been widely studied for probabilistic models. For simple regression an optimal myopic policy is easily tractable. However, for other tasks and with more complex models, such as classification with…

Machine Learning · Statistics 2011-12-30 Neil Houlsby , Ferenc Huszár , Zoubin Ghahramani , Máté Lengyel

We study a generalized geometric Brownian motion framework that incorporates both entries of new units and exit mechanisms for the current population, extending earlier stochastic resetting models where these rates are treated as identical.…

General Economics · Economics 2026-05-20 Suvam Pal , Viktor Stojkoski , Arnab Pal , Trifce Sandev

The construction of efficient thermal engines operating at finite times constitutes a fundamental and timely topic in nonequilibrium thermodynamics. We introduce a strategy for optimizing the performance of Brownian engines, based on a…

Statistical Mechanics · Physics 2021-08-04 C. E. Fernández Noa , Angel L. L. Stable , William G. C. Oropesa , Alexandre Rosas , C. E. Fiore

Gathering information about a system enables greater control over it. This principle lies at the core of information engines, which use measurement-based feedback to rectify thermal noise and convert information into work. Originating from…

Statistical Mechanics · Physics 2025-01-24 Rémi Goerlich , Laura Hoek , Omer Chor , Saar Rahav , Yael Roichman

Using a mechanical cantilever submitted to electrostatic feedback control, we investigate the thermodynamic properties of an information engine that extracts work from thermal fluctuations. The cantilever position is rapidly sampled and the…

This paper introduces the Bayesian Inference Engine (BIE), a general parallel, optimised software package for parameter inference and model selection. This package is motivated by the analysis needs of modern astronomical surveys and the…

Instrumentation and Methods for Astrophysics · Physics 2015-06-04 Martin D. Weinberg

Deep neural networks suffer from poor generalization to unseen environments when the underlying data distribution is different from that in the training set. By learning minimum sufficient representations from training data, the information…

Machine Learning · Computer Science 2021-10-13 Francesco Alesiani , Shujian Yu , Xi Yu

The ranking of experiments by expected information gain (EIG) in Bayesian experimental design is sensitive to changes in the model's prior distribution, and the approximation of EIG yielded by sampling will have errors similar to the use of…

Machine Learning · Statistics 2022-05-23 Jinwoo Go , Tobin Isaac

Optimal experimental design (OED) is a framework that leverages a mathematical model of the experiment to identify optimal conditions for conducting the experiment. Under a Bayesian approach, the design objective function is typically…

Computation · Statistics 2026-01-27 Thomas E. Coons , Xun Huan

This paper describes a general-purpose extension of max-value entropy search, a popular approach for Bayesian Optimisation (BO). A novel approximation is proposed for the information gain -- an information-theoretic quantity central to…

Machine Learning · Computer Science 2021-10-27 Henry B. Moss , David S. Leslie , Javier Gonzalez , Paul Rayson

A fundamental and intrinsic property of any device or natural system is its relaxation time relax, which is the time it takes to return to equilibrium after the sudden change of a control parameter [1]. Reducing $tau$ relax , is frequently…

Statistical Mechanics · Physics 2016-10-25 Ignacio Martinez , Artyom Petrosyan , David Guéry-Odelin , Emmanuel Trizac , Sergio Ciliberto

Grain boundary (GB) energy is a fundamental property that affects the form of grain boundary and plays an important role to unveil the behavior of polycrystalline materials. With a better understanding of grain boundary energy distribution…

Computational Physics · Physics 2020-02-04 Haoyu Wang , Srikanth Patala , Brian J. Reich