Image de couverture de livre

Faster Adaptive Optimization via Expected Gradient Outer Product Reparameterization

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	DePavia, Adela, Cruzado, Jose, Liang, Jiayou, Charisopoulos, Vasileios, Willett, Rebecca
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning Optimization and Control 90C06, 65K10, 90C30, 68T07
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Nonlinear tomographic reconstruction via nonsmooth optimization
par: Charisopoulos, Vasileios, et autres
Publié: (2024)

Convergence Conditions for Stochastic Line Search Based Optimization of Over-parametrized Models
par: Lapucci, Matteo, et autres
Publié: (2024)

Effectively Leveraging Momentum Terms in Stochastic Line Search Frameworks for Fast Optimization of Finite-Sum Problems
par: Lapucci, Matteo, et autres
Publié: (2024)

An Augmented Lagrangian Method for Training Recurrent Neural Networks
par: Wang, Yue, et autres
Publié: (2024)

Sample-wise Constrained Learning via a Sequential Penalty Approach with Applications in Image Processing
par: Lanzillotta, Francesca, et autres
Publié: (2026)

Line-search and Adaptive Step Sizes for Nonconvex-strongly-concave Minimax Optimization
par: Ma, Bohao, et autres
Publié: (2026)

Asymptotic Convergence and Stability of Adaptive Gradient Methods in Smooth Non-convex Optimization
par: Jin, Ruinan, et autres
Publié: (2026)

Proximal Limited-Memory Quasi-Newton Methods for Nonsmooth Nonconvex Optimization
par: Dahl, Simeon vom, et autres
Publié: (2026)

A MINRES-based Linesearch Algorithm for Nonconvex Optimization with Non-positive Curvature Detection
par: Zeng, Hanfeng, et autres
Publié: (2026)

Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency for Convex Optimization over Polytopes
par: Wang, Haoning, et autres
Publié: (2025)

Oracle complexities of augmented Lagrangian methods for nonsmooth manifold optimization
par: Deng, Kangkang, et autres
Publié: (2024)

Preconditioned subgradient method for composite optimization: overparameterization and fast convergence
par: Díaz, Mateo, et autres
Publié: (2025)

Fast Frank--Wolfe Algorithms with Adaptive Bregman Step-Size for Weakly Convex Functions
par: Takahashi, Shota, et autres
Publié: (2025)

Two-level overlapping additive Schwarz preconditioner for training scientific machine learning applications
par: Lee, Youngkyu, et autres
Publié: (2024)

Enhancing training of physics-informed neural networks using domain-decomposition based preconditioning strategies
par: Kopaničáková, Alena, et autres
Publié: (2023)

Accelerated Gradient Methods with Gradient Restart: Global Linear Convergence
par: Bao, Chenglong, et autres
Publié: (2024)

Gradient descent with adaptive stepsize converges (nearly) linearly under fourth-order growth
par: Davis, Damek, et autres
Publié: (2024)

A Single-Loop Stochastic Proximal Quasi-Newton Method for Large-Scale Nonsmooth Convex Optimization
par: Song, Yongcun, et autres
Publié: (2024)

A globalization of L-BFGS and the Barzilai-Borwein method for nonconvex unconstrained optimization
par: Mannel, Florian
Publié: (2024)

Monomial barrier functions for the box-constrained convex optimization problems
par: Fayed, Hatem
Publié: (2024)

A Layer Separation Optimization Framework for Cross-Entropy Training in Deep Learning
par: Liu, Yaru, et autres
Publié: (2026)

A non-monotone trust-region method with noisy oracles and additional sampling
par: Krejic, Natasa, et autres
Publié: (2023)

A structured L-BFGS method and its application to inverse problems
par: Mannel, Florian, et autres
Publié: (2023)

A structured L-BFGS method with diagonal scaling and its application to image registration
par: Mannel, Florian, et autres
Publié: (2024)

Anderson Accelerated Primal-Dual Hybrid Gradient for solving LP
par: Zhou, Yingxin, et autres
Publié: (2025)

$Q$-fully Quadratic Modeling and its Application in a Random Subspace Derivative-free Method
par: Chen, Yiwen, et autres
Publié: (2023)

On a globally convergent semismooth* Newton method in nonsmooth nonconvex optimization
par: Gfrerer, H.
Publié: (2024)

CLARSTA: A random subspace trust-region algorithm for convex-constrained derivative-free optimization
par: Chen, Yiwen, et autres
Publié: (2025)

A linesearch-type normal map-based semismooth Newton method for nonsmooth nonconvex composite optimization
par: Zeng, Hanfeng, et autres
Publié: (2026)

Bregman Stochastic Proximal Point Algorithm with Variance Reduction
par: Traoré, Cheik, et autres
Publié: (2025)

Mixed-integer linearity in nonlinear optimization: a trust region approach
par: De Marchi, Alberto
Publié: (2023)

Variational Properties of Decomposable Functions. Part I: Strict Epi-Calculus and Applications
par: Ouyang, Wenqing, et autres
Publié: (2023)

A Lasry-Lions envelope approach for mathematical programs with complementarity constraints
par: Wang, Jia, et autres
Publié: (2025)

Randomized block proximal method with locally Lipschitz continuous gradient
par: Pérez-Aros, Pedro, et autres
Publié: (2025)

Variational Properties of Decomposable Functions. Part II: Strong Second-Order Theory
par: Ouyang, Wenqing, et autres
Publié: (2023)

On the convergence of proximal gradient methods for convex simple bilevel optimization
par: Latafat, Puya, et autres
Publié: (2023)

Hybrid optimal control with mixed-integer Lagrangian methods
par: Nikitina, Viktoriya, et autres
Publié: (2024)

Affordable mixed-integer Lagrangian methods: optimality conditions and convergence analysis
par: De Marchi, Alberto
Publié: (2024)

Representation and Regression Problems in Neural Networks: Relaxation, Generalization, and Numerics
par: Liu, Kang, et autres
Publié: (2024)

Second-order Information Promotes Mini-Batch Robustness in Variance-Reduced Gradients
par: Garg, Sachin, et autres
Publié: (2024)