Image de couverture de livre

Convergence Analysis of Noisy Distributed Gradient Descent for Non-convex Optimization -- Saddle Point Escape

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qin, Lei, Cantoni, Michael, Pu, Ye
Format:	Preprint
Publié:	2025
Sujets:	Optimization and Control
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

On the Convergence of a Noisy Gradient Method for Non-convex Distributed Resource Allocation: Saddle Point Escape
par: Qin, Lei, et autres
Publié: (2025)

Convergence Analysis of EXTRA in Non-convex Distributed Optimization
par: Qin, Lei, et autres
Publié: (2025)

Curvature-Adaptive Perturbation and Subspace Descent for Robust Saddle Point Escape in High-Dimensional Optimization
par: Katende, Ronald, et autres
Publié: (2024)

Convergence Analysis of Stochastic Saddle Point Mirror Descent Algorithm -- A Projected Dynamical View Point
par: Paul, Anik Kumar, et autres
Publié: (2024)

Two-timescale EXTRA for Distributed Smooth Non-convex Optimization
par: Peng, Zeyu, et autres
Publié: (2024)

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
par: Yamamoto, Naoya, et autres
Publié: (2025)

Efficiently Escaping Saddle Points for Policy Optimization
par: Khorasani, Sadegh, et autres
Publié: (2023)

Gradient Descent for Convex and Smooth Noisy Optimization
par: Hu, Feifei, et autres
Publié: (2024)

High Probability Convergence Bounds for Non-convex Stochastic Gradient Descent with Sub-Weibull Noise
par: Madden, Liam, et autres
Publié: (2020)

Quantization Avoids Saddle Points in Distributed Optimization
par: Bo, Yanan, et autres
Publié: (2024)

Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
par: Martínez-Rubio, David, et autres
Publié: (2024)

Saddle Point Evasion via Curvature-Regularized Gradient Dynamics
par: Mudrik, Liraz, et autres
Publié: (2026)

Primal-dual Accelerated Mirror-Descent Method for Constrained Bilinear Saddle-Point Problems
par: Li, Weijian, et autres
Publié: (2024)

Accelerated Gradient Methods for Nonconvex Optimization: Escape Trajectories From Strict Saddle Points and Convergence to Local Minima
par: Dixit, Rishabh, et autres
Publié: (2023)

Decentralized Distributed Optimization for Saddle Point Problems
par: Rogozin, Alexander, et autres
Publié: (2021)

On the Convergence of Gradient Descent on Learning Transformers with Residual Connections
par: Qin, Zhen, et autres
Publié: (2025)

Last-Iterate Convergence of Anchored Gradient Descent
par: Cai, Yang, et autres
Publié: (2026)

One-Point Residual Feedback Algorithms for Distributed Online Convex and Non-convex Optimization
par: Wang, Yaowen, et autres
Publié: (2025)

Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
par: Cao, Daniel Yiming, et autres
Publié: (2025)

Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms
par: Huang, Minhui, et autres
Publié: (2021)

An LP-Based Approach for Bilinear Saddle Point Problem with Instance-dependent Guarantee and Noisy Feedback
par: Jiang, Jiashuo, et autres
Publié: (2026)

High Probability Convergence of Distributed Clipped Stochastic Gradient Descent with Heavy-tailed Noise
par: Yang, Yuchen, et autres
Publié: (2025)

Convergence Analysis of Stochastic Gradient Descent with MCMC Estimators
par: Li, Tianyou, et autres
Publié: (2023)

Asymmetric Perturbation in Solving Bilinear Saddle-Point Optimization
par: Abe, Kenshi, et autres
Publié: (2025)

Convergence of Spectral Descent for Non-smooth Optimization
par: Yang, Yixuan, et autres
Publié: (2026)

Point Convergence Analysis of the Accelerated Gradient Method for Multiobjective Optimization: Continuous and Discrete
par: Yin, Yingdong
Publié: (2025)

On Convergence of the Iteratively Preconditioned Gradient-Descent (IPG) Observer
par: Chakrabarti, Kushal, et autres
Publié: (2024)

Federated Composite Saddle Point Optimization
par: Bai, Site, et autres
Publié: (2023)

A Proof of the Exact Convergence Rate of Gradient Descent
par: Kim, Jungbin
Publié: (2024)

Distributed Saddle-Point Dynamics in Multilayer Networks
par: Rodríguez-Camargo, Christian D., et autres
Publié: (2025)

Quantitative Convergence Analysis of Projected Stochastic Gradient Descent for Non-Convex Losses via the Goldstein Subdifferential
par: Zheng, Yuping, et autres
Publié: (2025)

The Limit Points of (Optimistic) Gradient Descent in Min-Max Optimization
par: Daskalakis, Constantinos, et autres
Publié: (2018)

Accelerated Mirror Descent for Non-Euclidean Star-convex Functions
par: Lezane, Clement, et autres
Publié: (2024)

Accelerated Objective Gap and Gradient Norm Convergence for Gradient Descent via Long Steps
par: Grimmer, Benjamin, et autres
Publié: (2024)

Tight Analysis of Difference-of-Convex Algorithm (DCA) Improves Convergence Rates for Proximal Gradient Descent
par: Rotaru, Teodor, et autres
Publié: (2025)

A Communication-Efficient Stochastic Gradient Descent Algorithm for Distributed Nonconvex Optimization
par: Xie, Antai, et autres
Publié: (2024)

Projected Gradient Descent for Constrained Decision-Dependent Optimization
par: Wang, Zifan, et autres
Publié: (2025)

Convergence of Gradient Descent for Recurrent Neural Networks: A Nonasymptotic Analysis
par: Cayci, Semih, et autres
Publié: (2024)

Type-II Saddles and Probabilistic Stability of Stochastic Gradient Descent
par: Ziyin, Liu, et autres
Publié: (2023)

Learning Provably Improves the Convergence of Gradient Descent
par: Song, Qingyu, et autres
Publié: (2025)