Cover Image

Geometry of Critical Sets and Existence of Saddle Branches for Two-layer Neural Networks

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Leyang, Zhang, Yaoyu, Luo, Tao
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Optimization and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization
by: Zhang, Leyang, et al.
Published: (2023)

Uncovering Critical Sets of Deep Neural Networks via Sample-Independent Critical Lifting
by: Zhang, Leyang, et al.
Published: (2025)

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

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

Scale-Invariant Neural Network Optimization: Norm Geometry and Heavy-Tailed Noise
by: Zhang, Jiayu, et al.
Published: (2026)

Rethinking the Capacity of Graph Neural Networks for Branching Strategy
by: Chen, Ziang, et al.
Published: (2024)

Federated Composite Saddle Point Optimization
by: Bai, Site, et al.
Published: (2023)

On the Topology of Neural Network Superlevel Sets
by: Gharesifard, Bahman
Published: (2026)

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

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

Towards Optimal Branching of Linear and Semidefinite Relaxations for Neural Network Robustness Certification
by: Anderson, Brendon G., et al.
Published: (2021)

Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
by: Zhou, Duo, et al.
Published: (2024)

Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut
by: Cheng, Hongyu, et al.
Published: (2024)

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

Inertial Newton Algorithms Avoiding Strict Saddle Points
by: Castera, Camille
Published: (2021)

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

Heuristic Optimal Transport in Branching Networks
by: Andrecut, M.
Published: (2023)

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

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

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

Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity
by: Cao, Daniel Yiming, et al.
Published: (2025)

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

Convex Formulations for Training Two-Layer ReLU Neural Networks
by: Prakhya, Karthik, et al.
Published: (2024)

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

Geometry-Preserving Neural Architectures on Manifolds with Boundary
by: Elamvazhuthi, Karthik, et al.
Published: (2026)

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

Active Learning of Deep Neural Networks via Gradient-Free Cutting Planes
by: Zhang, Erica, et al.
Published: (2024)

SGD with Partial Hessian for Deep Neural Networks Optimization
by: Sun, Ying, et al.
Published: (2024)

Towards Quantifying the Hessian Structure of Neural Networks
by: Dong, Zhaorui, et al.
Published: (2025)

Convergence of Implicit Gradient Descent for Training Two-Layer Physics-Informed Neural Networks
by: Xu, Xianliang, et al.
Published: (2024)

Mean-Field Limits for Two-Layer Neural Networks Trained with Consensus-Based Optimization
by: De Deyn, William, et al.
Published: (2025)

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

Assessing and Enhancing Graph Neural Networks for Combinatorial Optimization: Novel Approaches and Application in Maximum Independent Set Problems
by: Hu, Chenchuhui
Published: (2024)

Analyzing Neural Network-Based Generative Diffusion Models through Convex Optimization
by: Zhang, Fangzhao, et al.
Published: (2024)

Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes
by: Zhang, Yuhao, et al.
Published: (2025)

Homotopy Relaxation Training Algorithms for Infinite-Width Two-Layer ReLU Neural Networks
by: Yang, Yahong, et al.
Published: (2023)

Data-driven Mixed Integer Optimization through Probabilistic Multi-variable Branching
by: Chen, Yanguang, et al.
Published: (2023)

Convergence Analysis of the Lion Optimizer in Centralized and Distributed Settings
by: Jiang, Wei, et al.
Published: (2025)

Provable Acceleration of Nesterov's Accelerated Gradient for Rectangular Matrix Factorization and Linear Neural Networks
by: Xu, Zhenghao, et al.
Published: (2024)

Projection-free Online Learning over Strongly Convex Sets
by: Wan, Yuanyu, et al.
Published: (2020)