Imagen de Portada

Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cao, Daniel Yiming, Chen, August Y., Sridharan, Karthik, Tang, Benjamin
Formato:	Preprint
Publicado:	2025
Materias:	Optimization and Control Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Langevin Dynamics: A Unified Perspective on Optimization via Lyapunov Potentials
por: Chen, August Y., et al.
Publicado: (2024)

Efficiently Escaping Saddle Points for Policy Optimization
por: Khorasani, Sadegh, et al.
Publicado: (2023)

Escaping Saddle Points for Nonsmooth Weakly Convex Functions via Perturbed Proximal Algorithms
por: Huang, Minhui, et al.
Publicado: (2021)

Hessian-guided Perturbed Wasserstein Gradient Flows for Escaping Saddle Points
por: Yamamoto, Naoya, et al.
Publicado: (2025)

On Linear Convergence in Smooth Convex-Concave Bilinearly-Coupled Saddle-Point Optimization: Lower Bounds and Optimal Algorithms
por: Kovalev, Dmitry, et al.
Publicado: (2024)

Simultaneous Learning and Optimization via Misspecified Saddle Point Problems
por: Ahmadi, Mohammad Mahdi, et al.
Publicado: (2025)

Federated Composite Saddle Point Optimization
por: Bai, Site, et al.
Publicado: (2023)

Proximal Point Method for Online Saddle Point Problem
por: Meng, Qing-xin, et al.
Publicado: (2024)

Quantization Avoids Saddle Points in Distributed Optimization
por: Bo, Yanan, et al.
Publicado: (2024)

Inertial Newton Algorithms Avoiding Strict Saddle Points
por: Castera, Camille
Publicado: (2021)

A Stochastic-Gradient-based Interior-Point Algorithm for Solving Smooth Bound-Constrained Optimization Problems
por: Curtis, Frank E., et al.
Publicado: (2023)

Exploring New Frontiers in Vertical Federated Learning: the Role of Saddle Point Reformulation
por: Beznosikov, Aleksandr, et al.
Publicado: (2026)

Online Min-Max Optimization: From Individual Regrets to Cumulative Saddle Points
por: Vyas, Abhijeet, et al.
Publicado: (2026)

Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation
por: Bylinkin, Dmitry, et al.
Publicado: (2025)

Smoothing the Edges: Smooth Optimization for Sparse Regularization using Hadamard Overparametrization
por: Kolb, Chris, et al.
Publicado: (2023)

Distributed Saddle-Point Problems: Lower Bounds, Near-Optimal and Robust Algorithms
por: Beznosikov, Aleksandr, et al.
Publicado: (2020)

MGDA Converges under Generalized Smoothness, Provably
por: Zhang, Qi, et al.
Publicado: (2024)

Tight Lower Bounds under Asymmetric High-Order Hölder Smoothness and Uniform Convexity
por: Bai, Cedar Site, et al.
Publicado: (2024)

From Saddle Points Toward Global Minima: A Newton-Type Method on Wasserstein Space
por: Lascu, Razvan-Andrei, et al.
Publicado: (2026)

Gradient-Variation Online Learning under Generalized Smoothness
por: Xie, Yan-Feng, et al.
Publicado: (2024)

Complexity Lower Bounds of Adaptive Gradient Algorithms for Non-convex Stochastic Optimization under Relaxed Smoothness
por: Crawshaw, Michael, et al.
Publicado: (2025)

(Almost) Smooth Sailing: Towards Numerical Stability of Neural Networks Through Differentiable Regularization of the Condition Number
por: Nenov, Rossen, et al.
Publicado: (2024)

Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
por: Zheng, Zihao, et al.
Publicado: (2026)

Decentralized Stochastic Nonconvex Optimization under the Relaxed Smoothness
por: Luo, Luo, et al.
Publicado: (2025)

AdaGrad under Anisotropic Smoothness
por: Liu, Yuxing, et al.
Publicado: (2024)

Provably Convergent Decentralized Optimization over Directed Graphs under Generalized Smoothness
por: Bo, Yanan, et al.
Publicado: (2026)

Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
por: Bassily, Raef, et al.
Publicado: (2024)

Provable Adaptivity of Adam under Non-uniform Smoothness
por: Wang, Bohan, et al.
Publicado: (2022)

Saddle Point Evasion via Curvature-Regularized Gradient Dynamics
por: Mudrik, Liraz, et al.
Publicado: (2026)

Graph Similarity Regularized Softmax for Semi-Supervised Node Classification
por: Yang, Yiming, et al.
Publicado: (2024)

Efficient First Order Method for Saddle Point Problems with Higher Order Smoothness
por: Wang, Nuozhou, et al.
Publicado: (2023)

WinQ: Accelerating Quantization-Aware Training of Language Models Around Saddle Points
por: Li, Dongyue, et al.
Publicado: (2026)

A Unified Theory of Stochastic Proximal Point Methods without Smoothness
por: Richtárik, Peter, et al.
Publicado: (2024)

On Generalization and Regularization via Wasserstein Distributionally Robust Optimization
por: Wu, Qinyu, et al.
Publicado: (2022)

On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond
por: Wang, Bohan, et al.
Publicado: (2024)

Near-Optimal Convergence of Accelerated Gradient Methods under Generalized and $(L_0, L_1)$-Smoothness
por: Tyurin, Alexander
Publicado: (2025)

High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise
por: Gorbunov, Eduard, et al.
Publicado: (2021)

Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks
por: Zhang, Leyang, et al.
Publicado: (2024)

Directional Convergence Near Small Initializations and Saddles in Two-Homogeneous Neural Networks
por: Kumar, Akshay, et al.
Publicado: (2024)

An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
por: Gong, Xiaochuan, et al.
Publicado: (2024)