Image de couverture de livre

Block Coordinate Descent for Neural Networks Provably Finds Global Minima

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Akiyama, Shunta
Format:	Preprint
Publié:	2025
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models
par: Sonoda, Sho, et autres
Publié: (2026)

Gradient Descent with Polyak's Momentum Finds Flatter Minima via Large Catapults
par: Phunyaphibarn, Prin, et autres
Publié: (2023)

Exponential Sample Complexity Separation between Flat and Hierarchical Agentic Theorem Provers
par: Sonoda, Sho, et autres
Publié: (2026)

Hybrid Coordinate Descent for Efficient Neural Network Learning Using Line Search and Gradient Descent
par: Hsiao, Yen-Che, et autres
Publié: (2024)

Geometry and Local Recovery of Global Minima of Two-layer Neural Networks at Overparameterization
par: Zhang, Leyang, et autres
Publié: (2023)

Differentially Private Random Block Coordinate Descent
par: Maranjyan, Artavazd, et autres
Publié: (2024)

Gradient Descent Converges Linearly to Flatter Minima than Gradient Flow in Shallow Linear Networks
par: Beneventano, Pierfrancesco, et autres
Publié: (2025)

Exploiting Block Coordinate Descent for Cost-Effective LLM Model Training
par: Liu, Zeyu, et autres
Publié: (2025)

SAFE: Finding Sparse and Flat Minima to Improve Pruning
par: Lee, Dongyeop, et autres
Publié: (2025)

Neural Networks with Complex-Valued Weights Have No Spurious Local Minima
par: Liu, Xingtu
Publié: (2021)

Zeroth-Order Optimization Finds Flat Minima
par: Zhang, Liang, et autres
Publié: (2025)

Coordinate Descent for Network Linearization
par: Rakhlin, Vlad, et autres
Publié: (2025)

Hidden State Differential Private Mini-Batch Block Coordinate Descent for Multi-convexity Optimization
par: Chen, Ding, et autres
Publié: (2024)

Gradient Descent with Provably Tuned Learning-rate Schedules
par: Sharma, Dravyansh
Publié: (2025)

Gradient Descent Finds Over-Parameterized Neural Networks with Sharp Generalization for Nonparametric Regression
par: Yang, Yingzhen, et autres
Publié: (2024)

Asynchronous Decentralized SGD under Non-Convexity: A Block-Coordinate Descent Framework
par: Zhou, Yijie, et autres
Publié: (2025)

FedBCD:Communication-Efficient Accelerated Block Coordinate Gradient Descent for Federated Learning
par: Liu, Junkang, et autres
Publié: (2026)

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

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon
par: Liang, Tongtong, et autres
Publié: (2025)

Randomized Block-Coordinate Optimistic Gradient Algorithms for Root-Finding Problems
par: Tran-Dinh, Quoc, et autres
Publié: (2023)

Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability
par: Gan, Eric
Publié: (2026)

DP-FedPGN: Finding Global Flat Minima for Differentially Private Federated Learning via Penalizing Gradient Norm
par: Liu, Junkang, et autres
Publié: (2025)

SMiLE: Provably Enforcing Global Relational Properties in Neural Networks
par: Francobaldi, Matteo, et autres
Publié: (2025)

A Block Coordinate Descent Method for Nonsmooth Composite Optimization under Orthogonality Constraints
par: Yuan, Ganzhao
Publié: (2023)

Provable and Practical Online Learning Rate Adaptation with Hypergradient Descent
par: Chu, Ya-Chi, et autres
Publié: (2025)

Provably Faster Gradient Descent via Long Steps
par: Grimmer, Benjamin
Publié: (2023)

Stochastic Gradient Descent for Two-layer Neural Networks
par: Cao, Dinghao, et autres
Publié: (2024)

Variational Stochastic Gradient Descent for Deep Neural Networks
par: Chen, Haotian, et autres
Publié: (2024)

Provably Bounding Neural Network Preimages
par: Kotha, Suhas, et autres
Publié: (2023)

Generative Autoencoding of Dropout Patterns
par: Maeda, Shunta
Publié: (2023)

Hidden Minima in Two-Layer ReLU Networks
par: Arjevani, Yossi
Publié: (2023)

Provable Privacy Attacks on Trained Shallow Neural Networks
par: Smorodinsky, Guy, et autres
Publié: (2024)

Provably Powerful Graph Neural Networks for Directed Multigraphs
par: Egressy, Béni, et autres
Publié: (2023)

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks
par: Nichani, Eshaan, et autres
Publié: (2023)

Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
par: Guo, Zhishuai, et autres
Publié: (2026)

Global Minima by Penalized Full-dimensional Scaling
par: de Leeuw, Jan
Publié: (2024)

Generalization Bounds of Stochastic Gradient Descent in Homogeneous Neural Networks
par: Ma, Wenquan, et autres
Publié: (2026)

Generalization Guarantees of Gradient Descent for Multi-Layer Neural Networks
par: Wang, Puyu, et autres
Publié: (2023)

Asynchronous Distributed Reinforcement Learning for LQR Control via Zeroth-Order Block Coordinate Descent
par: Jing, Gangshan, et autres
Publié: (2021)

Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
par: Zhang, Chenyang, et autres
Publié: (2026)