Imagen de Portada

Spectral Preconditioning for Gradient Methods on Graded Non-convex Functions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Doikov, Nikita, Stich, Sebastian U., Jaggi, Martin
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 Convergence of Incremental Gradient for Non-Convex Smooth Functions
por: Koloskova, Anastasia, et al.
Publicado: (2023)

Gradient-Normalized Smoothness for Optimization with Approximate Hessians
por: Semenov, Andrei, et al.
Publicado: (2025)

Unified Convergence Theory of Stochastic and Variance-Reduced Cubic Newton Methods
por: Chayti, El Mahdi, et al.
Publicado: (2023)

Improving Stochastic Cubic Newton with Momentum
por: Chayti, El Mahdi, et al.
Publicado: (2024)

Universal Reduced-Operator Method and High-Order Global Curvature Bounds
por: Doikov, Nikita, et al.
Publicado: (2025)

Non-convex Stochastic Composite Optimization with Polyak Momentum
por: Gao, Yuan, et al.
Publicado: (2024)

Complexity of Minimizing Regularized Convex Quadratic Functions
por: Thomsen, Daniel Berg, et al.
Publicado: (2024)

On the Complexity of Lower-Order Implementations of Higher-Order Methods
por: Doikov, Nikita, et al.
Publicado: (2025)

Optimizing $(L_0, L_1)$-Smooth Functions by Gradient Methods
por: Vankov, Daniil, et al.
Publicado: (2024)

Cubic regularized subspace Newton for non-convex optimization
por: Zhao, Jim, et al.
Publicado: (2024)

Efficient Gradient Methods for Distributed Saddle Problems
por: Luo, Ruichen, et al.
Publicado: (2026)

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
por: Zhang, Siqi, et al.
Publicado: (2023)

Stabilized Proximal-Point Methods for Federated Optimization
por: Jiang, Xiaowen, et al.
Publicado: (2024)

Non-Convex Federated Optimization under Cost-Aware Client Selection
por: Jiang, Xiaowen, et al.
Publicado: (2025)

Stochastic Gradient Methods with Preconditioned Updates
por: Sadiev, Abdurakhmon, et al.
Publicado: (2022)

Scalable Decentralized Learning with Teleportation
por: Takezawa, Yuki, et al.
Publicado: (2025)

Nonlinearly Preconditioned Gradient Methods: Momentum and Stochastic Analysis
por: Oikonomidis, Konstantinos, et al.
Publicado: (2025)

Nonlinearly Preconditioned Gradient Methods under Generalized Smoothness
por: Oikonomidis, Konstantinos, et al.
Publicado: (2025)

Federated Optimization with Doubly Regularized Drift Correction
por: Jiang, Xiaowen, et al.
Publicado: (2024)

Locally Adaptive Federated Learning
por: Mukherjee, Sohom, et al.
Publicado: (2023)

Monotone and nonmonotone linearized block coordinate descent methods for nonsmooth composite optimization problems
por: Nabou, Yassine, et al.
Publicado: (2025)

Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
por: Rodomanov, Anton, et al.
Publicado: (2024)

On the Convergence of a Noisy Gradient Method for Non-convex Distributed Resource Allocation: Saddle Point Escape
por: Qin, Lei, et al.
Publicado: (2025)

Preconditioned Nonlinear Conjugate Gradient Method for Real-time Interior-point Hyperelasticity
por: Shen, Xing, et al.
Publicado: (2024)

On Convergence of the Iteratively Preconditioned Gradient-Descent (IPG) Observer
por: Chakrabarti, Kushal, et al.
Publicado: (2024)

Towards Faster Decentralized Stochastic Optimization with Communication Compression
por: Islamov, Rustem, et al.
Publicado: (2024)

Monotone Near-Zero-Sum Games: A Generalization of Convex-Concave Minimax
por: Luo, Ruichen, et al.
Publicado: (2025)

Accelerated Distributed Optimization with Compression and Error Feedback
por: Gao, Yuan, et al.
Publicado: (2025)

FedMuon: Federated Learning with Bias-corrected LMO-based Optimization
por: Takezawa, Yuki, et al.
Publicado: (2025)

Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization
por: Takezawa, Yuki, et al.
Publicado: (2025)

Model Predictive Path Integral Control as Preconditioned Gradient Descent
por: Fazlyab, Mahyar, et al.
Publicado: (2026)

Accelerated Mirror Descent for Non-Euclidean Star-convex Functions
por: Lezane, Clement, et al.
Publicado: (2024)

Mirror and Preconditioned Gradient Descent in Wasserstein Space
por: Bonet, Clément, et al.
Publicado: (2024)

Revisiting LocalSGD and SCAFFOLD: Improved Rates and Missing Analysis
por: Luo, Ruichen, et al.
Publicado: (2025)

Convergence Analysis of Noisy Distributed Gradient Descent for Non-convex Optimization -- Saddle Point Escape
por: Qin, Lei, et al.
Publicado: (2025)

High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise
por: Madden, Liam, et al.
Publicado: (2020)

A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training
por: Angino, Andrea, et al.
Publicado: (2026)

Constrained Stochastic Spectral Preconditioning Converges for Nonconvex Objectives
por: Oikonomidis, Konstantinos, et al.
Publicado: (2026)

An Inexact Preconditioned Zeroth-order Proximal Method for Composite Optimization
por: Liu, Shanglin, et al.
Publicado: (2024)

A Near-optimal Method for Linearly Constrained Composite Non-convex Non-smooth Problems
por: Liu, Wei, et al.
Publicado: (2025)