English
Related papers

Related papers: Born-Infeld (BI) for AI: Energy-Conserving Descent…

200 papers

Entropic dynamics (ED) is a framework that allows one to derive quantum theory as a Hamilton-Killing flow on the cotangent bundle of a statistical manifold. These flows are such that they preserve the symplectic and the (information) metric…

Quantum Physics · Physics 2025-11-25 Ariel Caticha

As we march towards the age of ubiquitous intelligence, we note that AI and intelligence are progressively moving from the cloud to the edge. The success of Edge-AI is pivoted on innovative circuits and hardware that can enable inference…

Hardware Architecture · Computer Science 2022-02-24 Zishen Wan , Ashwin Sanjay Lele , Arijit Raychowdhury

This work explores the global optimization problem of finding lowest-energy configurations (ground states) in disordered continuous spins models from statistical physics, with a particular focus on the random field XY model. Due to an…

Optimization and Control · Mathematics 2026-05-07 Ramgopal Agrawal , Lorenzo Ciarpaglini , Enzo Marinari , Marco Sciandrone , Diego Scuppa , Elisa Trasatti

Energy-based models (EBMs) implement inference as gradient descent on a learned Lyapunov function, yielding interpretable, structure-preserving alternatives to black-box neural ODEs and aligning naturally with physical AI. Yet their use in…

Systems and Control · Electrical Eng. & Systems 2026-04-03 Simone Betteti , Luca Laurenti

In this paper, the CONFIG algorithm, a simple and provably efficient constrained global optimization algorithm, is applied to optimize the closed-loop control performance of an unknown system with unmodeled constraints. Existing Gaussian…

Optimization and Control · Mathematics 2022-12-20 Wenjie Xu , Yuning Jiang , Bratislav Svetozarevic , Colin N. Jones

The space fractional Cahn-Hilliard phase-field model is more adequate and accurate in the description of the formation and phase change mechanism than the classical Cahn-Hilliard model. In this article, we propose a temporal second-order…

Numerical Analysis · Mathematics 2021-05-13 Yong-Liang Zhao , Meng Li , Alexander Ostermann , Xian-Ming Gu

Turbulence is characterised by chaotic dynamics and a high-dimensional state space, which make this phenomenon challenging to predict. However, turbulent flows are often characterised by coherent spatiotemporal structures, such as vortices…

Fluid Dynamics · Physics 2023-06-21 Nguyen Anh Khoa Doan , Alberto Racca , Luca Magri

Bayesian optimization (BO) is an efficient framework for optimization of black-box objectives when function evaluations are costly and gradient information is not easily accessible. BO has been successfully applied to automate the task of…

Machine Learning · Computer Science 2024-07-09 Pallavi Mitra , Felix Biessmann

For a wide class of Hamiltonians, a novel method to obtain lower and upper bounds for the lowest energy is presented. Unlike perturbative or variational techniques, this method does not involve the computation of any integral (a…

Quantum Physics · Physics 2009-11-10 Amaury Mouchet

We pose the problem of transferring a Bose-Einstein Condensate (BEC) from one side of a double-well potential to the other as an optimal control problem for determining the time-dependent form of the potential. We derive a reduced dynamical…

Pattern Formation and Solitons · Physics 2023-05-24 J. Adriazola , R. H. Goodman , P. G. Kevrekidis

This work explores optimization methods on hyperbolic manifolds. Building on Riemannian optimization principles, we extend the Hyperbolic Stochastic Gradient Descent (a specialization of Riemannian SGD) to a Hyperbolic Adam optimizer. While…

Machine Learning · Computer Science 2025-10-01 Yanke Wang , Kyriakos Flouris

An adaptive implicit-explicit (IMEX) BDF2 scheme is investigated on generalized SAV approach for the Cahn-Hilliard equation by combining with Fourier spectral method in space. It is proved that the modified energy dissipation law is…

Numerical Analysis · Mathematics 2022-11-04 Yifan Wei , Jiwei Zhang , Chengchao Zhao , Yanmin Zhao

We propose enforcing constraints on Model-Based Diffusion by introducing emerging barrier functions inspired by interior point methods. We demonstrate that the standard Model-Based Diffusion algorithm can lead to catastrophic performance…

Robotics · Computer Science 2026-03-10 Raghav Mishra , Ian R. Manchester

Autonomous vehicles (AVs) present a unique opportunity to improve the sustainability of transportation systems by adopting eco-driving strategies that reduce energy consumption and emissions. This paper introduces a novel surrogate model…

Optimization and Control · Mathematics 2025-06-06 Andreas Hadjigeorgiou , Stelios Timotheou

Conventional deep learning prioritizes unconstrained optimization, yet biological systems operate under strict metabolic constraints. We propose that these physical constraints shape dynamics to function not as limitations, but as a…

Machine Learning · Computer Science 2026-01-23 Xia Chen

A disordered version of the one dimensional asymmetric exclusion model where the particle hopping rates are quenched random variables is studied. The steady state is solved exactly by use of a matrix product. It is shown how the phenomenon…

Condensed Matter · Physics 2009-10-28 M. R. Evans

Consensus-based optimization (CBO) is a powerful and versatile zero-order multi-particle method designed to provably solve high-dimensional global optimization problems, including those that are genuinely nonconvex or nonsmooth. The method…

Optimization and Control · Mathematics 2026-02-13 Massimo Fornasier , Hui Huang , Jona Klemenc , Greta Malaspina

We present AI Poincar\'e, a machine learning algorithm for auto-discovering conserved quantities using trajectory data from unknown dynamical systems. We test it on five Hamiltonian systems, including the gravitational 3-body problem, and…

Machine Learning · Computer Science 2021-05-10 Ziming Liu , Max Tegmark

The development of novel autonomous underwater gliders has been hindered by limited shape diversity, primarily due to the reliance on traditional design tools that depend heavily on manual trial and error. Building an automated design…

Edge intelligence enables AI inference at the network edge, co-located with or near the radio access network, rather than in centralized clouds or on mobile devices. It targets low-latency, resource-constrained applications with large data…

Networking and Internet Architecture · Computer Science 2026-01-26 Jaume Anguera Peris , Joakim Jaldén
‹ Prev 1 3 4 5 6 7 10 Next ›