English
Related papers

Related papers: Learning Maximum Entropy Models from finite size d…

200 papers

Entropy production is a universal measure of irreversibility and energy dissipation in physical, chemical, and biological systems operating far from equilibrium. However, quantifying and spatiotemporally localising it in complex processes…

Statistical Mechanics · Physics 2026-05-18 Biswajit Das , Sreekanth K Manikandan

The classical problem of moments is addressed by the maximum entropy approach for one-dimensional discrete distributions. The numerical technique of adaptive support approximation is proposed to reconstruct the distributions in the region…

Numerical Analysis · Mathematics 2014-09-02 Alexander Andreychenko , Linar Mikeev , Verena Wolf

Although instantaneous interactions are unphysical, a large variety of maximum entropy statistical inference methods match the model-inferred and the empirically-measured equal-time correlation functions. Focusing on collective motion of…

This article proposes an improved trajectory optimization approach for stochastic optimal control of dynamical systems affected by measurement noise by combining optimal control with maximum likelihood techniques to improve the reduction of…

Systems and Control · Electrical Eng. & Systems 2023-12-25 Prakash Mallick , Zhiyong Chen

This paper studies a classic maximum entropy sampling problem (MESP), which aims to select the most informative principal submatrix of a prespecified size from a covariance matrix. MESP has been widely applied to many areas, including…

Machine Learning · Statistics 2023-05-02 Yongchun Li , Weijun Xie

We propose a method for transforming probability distributions so that parameters of interest are forced into a specified distribution. We prove that this approach is the maximum entropy choice, and provide a motivating example applicable…

Statistics Theory · Mathematics 2019-03-13 Will Handley , Marius Millea

Optimal control of stochastic nonlinear dynamical systems is a major challenge in the domain of robot learning. Given the intractability of the global control problem, state-of-the-art algorithms focus on approximate sequential optimization…

Machine Learning · Computer Science 2020-04-23 Joe Watson , Hany Abdulsamad , Jan Peters

We study the approach towards equilibrium in a dynamic Ising model, the Q2R cellular automaton, with microscopic reversibility and conserved energy for an infinite one-dimensional system. Starting from a low-entropy state with positive…

Statistical Mechanics · Physics 2017-08-02 Kristian Lindgren , Eckehard Olbrich

While most approaches to the problem of Inverse Reinforcement Learning (IRL) focus on estimating a reward function that best explains an expert agent's policy or demonstrated behavior on a control task, it is often the case that such…

Machine Learning · Computer Science 2020-05-01 Dexter R. R. Scobee , S. Shankar Sastry

End-to-end deep trainable models are about to exceed the performance of the traditional handcrafted compression techniques on videos and images. The core idea is to learn a non-linear transformation, modeled as a deep neural network,…

Image and Video Processing · Electrical Eng. & Systems 2022-09-05 Muhammet Balcilar , Bharath Damodaran , Pierre Hellier

We use the method of Maximum (relative) Entropy to process information in the form of observed data and moment constraints. The generic "canonical" form of the posterior distribution for the problem of simultaneous updating with data and…

Data Analysis, Statistics and Probability · Physics 2016-09-08 Adom Giffin , Ariel Caticha

Policy gradient algorithms have driven many recent advancements in language model reasoning. An appealing property is their ability to learn from exploration on their own trajectories, a process crucial for fostering diverse and creative…

Machine Learning · Computer Science 2026-03-13 Aleksei Petrenko , Ben Lipkin , Kevin Chen , Erik Wijmans , Marco Cusumano-Towner , Raja Giryes , Philipp Krähenbühl

Trajectory following is one of the complicated control problems when its dynamics are nonlinear, stochastic and include a large number of parameters. The problem has significant difficulties including a large number of trials required for…

Robotics · Computer Science 2019-02-14 Ali Lenjani

In many settings (e.g., robotics) demonstrations provide a natural way to specify tasks; however, most methods for learning from demonstrations either do not provide guarantees that the artifacts learned for the tasks, such as rewards or…

Machine Learning · Computer Science 2020-05-19 Marcell Vazquez-Chanlatte , Sanjit A. Seshia

Recent works in high-dimensional model-predictive control and model-based reinforcement learning with learned dynamics and reward models have resorted to population-based optimization methods, such as the Cross-Entropy Method (CEM), for…

Machine Learning · Computer Science 2020-04-21 Homanga Bharadhwaj , Kevin Xie , Florian Shkurti

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

Deep neural networks, when optimized with sufficient data, provide accurate representations of high-dimensional functions; in contrast, function approximation techniques that have predominated in scientific computing do not scale well with…

Data Analysis, Statistics and Probability · Physics 2021-03-15 Grant M. Rotskoff , Andrew R. Mitchell , Eric Vanden-Eijnden

This paper addresses the estimation of parameters of a Bayesian network from incomplete data. The task is usually tackled by running the Expectation-Maximization (EM) algorithm several times in order to obtain a high log-likelihood…

Machine Learning · Computer Science 2015-03-19 Giorgio Corani , Cassio P. De Campos

We refine a recently-proposed class of local entropic loss functions by restricting the smoothening regularization to only a subset of weights. The new loss functions are referred to as partial local entropies. They can adapt to the…

Machine Learning · Computer Science 2021-04-14 Daniele Musso

Model-based reinforcement learning (RL) algorithms can attain excellent sample efficiency, but often lag behind the best model-free algorithms in terms of asymptotic performance. This is especially true with high-capacity parametric…

Machine Learning · Computer Science 2018-11-05 Kurtland Chua , Roberto Calandra , Rowan McAllister , Sergey Levine