English
Related papers

Related papers: Equilibrium Propagation for Learning in Lagrangian…

200 papers

This paper presents L-Learning, a novel data-driven control framework for robotics that integrates Lyapunov stability theory with Lagrangian mechanics to enhance trajectory tracking performance. While traditional control methods often…

Robotics · Computer Science 2026-05-27 Quan Quan , Hao Li

In this paper we present a new quantum-trajectory based treatment of quantum dynamics suitable for dissipative systems. Starting from a de Broglie/Bohm-like representation of the quantum density matrix, we derive and define quantum…

Quantum Physics · Physics 2007-05-23 Jeremy B. Maddox , Eric R. Bittner

The continuous dynamical system approach to deep learning is explored in order to devise alternative frameworks for training algorithms. Training is recast as a control problem and this allows us to formulate necessary optimality conditions…

Machine Learning · Computer Science 2018-06-05 Qianxiao Li , Long Chen , Cheng Tai , Weinan E

This paper provides a new tauberian approach to the study of quantitative time asymptotics of collisionless transport semigroups with general diffuse boundary operators. We obtain an (almost) optimal algebraic rate of convergence to…

Analysis of PDEs · Mathematics 2021-04-15 Bertrand Lods , Mustapha Mokhtar-Kharroubi

We present a numerical framework for modeling extended hyperelastic bodies based on a Lagrangian formulation of general relativistic elasticity theory. We use finite element methods to discretize the body, then use the semi--discrete action…

General Relativity and Quantum Cosmology · Physics 2023-10-18 Nishita Jadoo , J. David Brown , Charles R. Evans

Minimizing non-convex and high-dimensional objective functions is challenging, especially when training modern deep neural networks. In this paper, a novel approach is proposed which divides the training process into two consecutive phases…

Machine Learning · Computer Science 2017-10-11 Nanyang Ye , Zhanxing Zhu , Rafal K. Mantiuk

The incorporation of appropriate inductive bias plays a critical role in learning dynamics from data. A growing body of work has been exploring ways to enforce energy conservation in the learned dynamics by encoding Lagrangian or…

Robotics · Computer Science 2021-11-15 Yaofeng Desmond Zhong , Biswadip Dey , Amit Chakraborty

Human mobility, enabled by diverse transportation modes, is fundamental to urban functionality. Studying these movements across scales-from microscopic to macroscopic-yields valuable insights into urban dynamics. Local adaptation and…

Disordered Systems and Neural Networks · Physics 2026-05-21 Babak Benam , Abolfazl Ramezanpour

Advanced traffic navigation systems, which provide routing recommendations to drivers based on real-time congestion information, are nowadays widely adopted by roadway transportation users. Yet, the emerging effects on the traffic dynamics…

Optimization and Control · Mathematics 2023-12-19 Gianluca Bianchin , Fabio Pasqualetti

Backpropagation is typically presented as a symbolic procedure: a backward pass topologically distinct from inference, with non-local error signals and synchronous global clocking, features with no clear analog in physical reality. Existing…

Machine Learning · Computer Science 2026-05-12 Antonino Emanuele Scurria

Equivariant neural networks have been widely used in a variety of applications due to their ability to generalize well in tasks where the underlying data symmetries are known. Despite their successes, such networks can be difficult to…

Machine Learning · Computer Science 2025-01-06 Stefanos Pertigkiozoglou , Evangelos Chatzipantazis , Shubhendu Trivedi , Kostas Daniilidis

The energy Casimir method is an effective controller design approach to stabilize port-Hamiltonian systems at a desired equilibrium. However, its application relies on the availability of suitable Casimir and Lyapunov functions, whose…

Systems and Control · Electrical Eng. & Systems 2022-03-29 Liang Xu , Muhammad Zakwan , Giancarlo Ferrari-Trecate

We present an approach to construct approximate Koopman-type decompositions for dynamical systems depending on static or time-varying parameters. Our method simultaneously constructs an invariant subspace and a parametric family of…

Optimization and Control · Mathematics 2024-11-12 Yue Guo , Milan Korda , Ioannis G. Kevrekidis , Qianxiao Li

Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging. Standard approaches often rely on short-time…

Machine Learning · Statistics 2026-04-28 Ludovico T. Giorgini

Learning processes by exploiting restricted domain knowledge is an important task across a plethora of scientific areas, with more and more hybrid training methods additively combining data-driven and model-based approaches. Although the…

Machine Learning · Computer Science 2025-01-17 Yann Claes , Vân Anh Huynh-Thu , Pierre Geurts

Hybrid dynamical systems pose significant challenges for effective planning and control, especially when additional constraints such as obstacle avoidance, state boundaries, and actuation limits are present. In this letter, we extend the…

Systems and Control · Electrical Eng. & Systems 2025-10-24 Pietro Noah Crestaz , Gokhan Alcan , Ville Kyrki

In classical mechanics, external constraints on the dynamical variables can be easily implemented within the Lagrangian formulation. Conversely, the extension of this idea to the quantum realm, which dates back to Dirac, has proven…

Quantum Physics · Physics 2021-02-25 André M. Timpanaro , Sascha Wald , Fernando Semião , Gabriel T. Landi

By extending the extreme learning machine by additional control inputs, we achieved almost complete reproduction of bifurcation structures of dynamical systems. The learning ability of the proposed neural network system is striking in that…

Chaotic Dynamics · Physics 2024-10-21 Satoru Tadokoro , Akihiro Yamaguchi , Takao Namiki , Ichiro Tsuda

In this work, we investigate the use of data-driven equation discovery for dynamical systems to model and forecast continuous-time dynamics of unconstrained optimization problems. To avoid expensive evaluations of the objective function and…

Optimization and Control · Mathematics 2026-02-19 Grant Norman , Conor Rowan , Kurt Maute , Alireza Doostan

In regimes where inertia is negligible, the temporal evolution is governed by overdamped dynamics. This limit is particularly relevant in soft-matter contexts, such as polymers, colloidal suspensions, and processes occurring at the cellular…

Soft Condensed Matter · Physics 2026-02-24 Marc Berneman , Daniel Hexner