Imagen de Portada

A new perspective on the learning dynamics for a class of learning problems via averaged gradient systems coupled with diffusion-transmutation processes

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autor principal:	Befekadu, Getachew K.
Formato:	Preprint
Publicado:	2024
Materias:	Optimization and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

On improving generalization in a class of learning problems with the method of small parameters for weakly-controlled optimal gradient systems
por: Befekadu, Getachew K.
Publicado: (2024)

On characterizing optimal learning trajectories in a class of learning problems
por: Befekadu, Getachew K
Publicado: (2025)

A brief note on learning problem with global perspectives
por: Befekadu, Getachew K.
Publicado: (2026)

A naive aggregation algorithm for improving generalization in a class of learning problems
por: Befekadu, Getachew K
Publicado: (2024)

Further extensions on the successive approximation method for hierarchical optimal control problems and its application to learning
por: Befekadu, Getachew K.
Publicado: (2024)

A successive approximation method in functional spaces for hierarchical optimal control problems and its application to learning
por: Befekadu, Getachew K.
Publicado: (2024)

Embedding generalization within the learning dynamics: An approach based-on sample path large deviation theory
por: Befekadu, Getachew K.
Publicado: (2024)

A class of generalized Nesterov's accelerated gradient method from dynamical perspective
por: Cheng, Xu, et al.
Publicado: (2025)

Adaptive generalized conditional gradient method for multiobjective optimization
por: Gebrie, Anteneh Getachew, et al.
Publicado: (2024)

A decision-theoretic model for a principal-agent collaborative learning problem
por: Befekadu, Getachew K
Publicado: (2024)

Operator learning for prescribed-time stabilization of reaction-diffusion systems
por: Lyu, Kaijing, et al.
Publicado: (2026)

Adaptive primal dual hybrid gradient algorithms based on average spectrum for saddle point problems
por: Xu, Shengjie, et al.
Publicado: (2026)

Improved sampling via learned diffusions
por: Richter, Lorenz, et al.
Publicado: (2023)

An Insensitizing control problem involving tangential gradient terms for a reaction-diffusion equation with dynamic boundary conditions
por: Santos, Mauricio C., et al.
Publicado: (2024)

A learning model predictive control for virtual coupling in railroads
por: Vaquero-Serrano, Miguel A., et al.
Publicado: (2025)

Unknown input observer design for a class of coupled wave PDE systems
por: Ghaderi, Najmeh, et al.
Publicado: (2025)

A new polynomially solvable class of quadratic optimization problems with box constraints
por: Hladík, Milan, et al.
Publicado: (2019)

Doubly nonlinear diffusive PDEs: new existence results via generalized Wasserstein gradient flows
por: Caillet, Thibault, et al.
Publicado: (2024)

Independent policy gradient-based reinforcement learning for economic and reliable energy management of multi-microgrid systems
por: Hu, Junkai, et al.
Publicado: (2025)

A deep learning method for solving stochastic optimal control problems driven by fully-coupled FBSDEs
por: Ji, Shaolin, et al.
Publicado: (2022)

Accelerated windowing for the crew rostering problem with machine learning
por: Racette, Philippe, et al.
Publicado: (2025)

Convergence of gradient flow for learning convolutional neural networks
por: Diederen, Jona-Maria, et al.
Publicado: (2026)

A primal-dual perspective for distributed TD-learning
por: Lim, Han-Dong, et al.
Publicado: (2023)

EM++: A parameter learning framework for stochastic switching systems
por: Wang, Renzi, et al.
Publicado: (2024)

When do spectral gradient updates help in deep learning?
por: Davis, Damek, et al.
Publicado: (2025)

Concave tents: a new tool for constructing concave reformulations of a large class of nonconvex optimization problems
por: Gabl, Markus
Publicado: (2024)

Joint learning of a network of linear dynamical systems via total variation penalization
por: Donnat, Claire, et al.
Publicado: (2025)

Primal-dual policy learning for mean-field stochastic LQR problem
por: Jiang, Xiushan, et al.
Publicado: (2025)

Gradient flow in the kernel learning problem
por: Li, Yang, et al.
Publicado: (2025)

A hybrid deep learning method for finite-horizon mean-field game problems
por: Zhang, Yu, et al.
Publicado: (2023)

Computationally efficient solution of mixed integer model predictive control problems via machine learning aided Benders Decomposition
por: Mitrai, Ilias, et al.
Publicado: (2023)

A matheuristic approach for an integrated lot-sizing and scheduling problem with a period-based learning effect
por: Rohaninejad, Mohammad, et al.
Publicado: (2024)

An equivalent reformulation and multi-proximity gradient algorithms for a class of nonsmooth fractional programming
por: Zhou, Junpeng, et al.
Publicado: (2023)

Riemannian conditional gradient methods for composite optimization problems
por: Chen, Kangming, et al.
Publicado: (2024)

Simulation-based Bayesian inference with ameliorative learned summary statistics -- Part I
por: Befekadu, Getachew K.
Publicado: (2026)

Model-free $H_{\infty}$ control of Itô stochastic system via off-policy reinforcement learning
por: Guo, Jing Guo Jing, et al.
Publicado: (2024)

Stochastic optimization of a mixed moving average process for controlling non-Markovian streamflow environments
por: Yoshioka, Hidekazu, et al.
Publicado: (2022)

A neural network approach to learning solutions of a class of elliptic variational inequalities
por: Alphonse, Amal, et al.
Publicado: (2024)

Time-consistency in the mean-variance problem: A new perspective
por: Bäuerle, Nicole, et al.
Publicado: (2023)

Solving maximally comonotone inclusion problems via an implicit Newton-like inertial dynamical system and its discretization
por: Tan, Z. Z., et al.
Publicado: (2024)