Copertina

Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Liu, Bing, Kong, Boao, Lu, Limin, Yuan, Kun, Zhao, Chengcheng
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes
di: Kong, Boao, et al.
Pubblicazione: (2026)

Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks
di: Hu, Zhaobo, et al.
Pubblicazione: (2026)

Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity
di: Kong, Boao, et al.
Pubblicazione: (2024)

SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
di: Zhu, Shuchen, et al.
Pubblicazione: (2024)

Doubly Stochastic Matrices and Modified Laplacian Matrices of Graphs
di: Andrade, Enide, et al.
Pubblicazione: (2025)

DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks
di: Jeong, Eunjeong, et al.
Pubblicazione: (2024)

CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
di: Kong, Boao, et al.
Pubblicazione: (2025)

Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization
di: Hu, Rizhen, et al.
Pubblicazione: (2026)

Doubly Stochastic Adaptive Neighbors Clustering via the Marcus Mapping
di: Yuan, Jinghui, et al.
Pubblicazione: (2024)

Demystifying SGD with Doubly Stochastic Gradients
di: Kim, Kyurae, et al.
Pubblicazione: (2024)

PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution
di: Wang, Lina, et al.
Pubblicazione: (2025)

ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
di: Shahbazi, Ashkan, et al.
Pubblicazione: (2025)

Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
di: Vaswani, Sharan, et al.
Pubblicazione: (2025)

The Homogeneity Trap: Spectral Collapse in Doubly-Stochastic Deep Networks
di: Liu, Yizhi
Pubblicazione: (2026)

Doubly Stochastic Mean-Shift Clustering
di: Trigano, Tom, et al.
Pubblicazione: (2026)

Learning Symmetries via Weight-Sharing with Doubly Stochastic Tensors
di: van der Linden, Putri A., et al.
Pubblicazione: (2024)

BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
di: Zhang, Hengrui, et al.
Pubblicazione: (2026)

Stochastic Rounding Implicitly Regularizes Tall-and-Thin Matrices
di: Dexter, Gregory, et al.
Pubblicazione: (2024)

MARS-M: When Variance Reduction Meets Matrices
di: Liu, Yifeng, et al.
Pubblicazione: (2025)

Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization
di: Mazumdar, Abhijit, et al.
Pubblicazione: (2026)

Decentralized Optimization over Time-Varying Row-Stochastic Digraphs
di: Liang, Liyuan, et al.
Pubblicazione: (2025)

Stochastic Trace Optimization of Parameter Dependent Matrices Based on Statistical Learning Theory
di: Saibaba, Arvind K., et al.
Pubblicazione: (2025)

Quantum Doubly Stochastic Transformers
di: Born, Jannis, et al.
Pubblicazione: (2025)

ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projection
di: Tran, Huy, et al.
Pubblicazione: (2026)

A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schrödinger Equations
di: Cole, Frank, et al.
Pubblicazione: (2026)

Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
di: Wu, Yuchen, et al.
Pubblicazione: (2024)

Enhancing Parallelism in Decentralized Stochastic Convex Optimization
di: Eisen, Ofri, et al.
Pubblicazione: (2025)

Clapping: Removing Per-sample Storage for Pipeline Parallel Distributed Optimization with Communication Compression
di: Kong, Boao, et al.
Pubblicazione: (2025)

Adjacent Leader Decentralized Stochastic Gradient Descent
di: He, Haoze, et al.
Pubblicazione: (2024)

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
di: Fernando, Heshan, et al.
Pubblicazione: (2022)

Learning Fill-in Reduction Ordering via Graph Policy Optimization for Sparse Matrices
di: Li, Ziwei, et al.
Pubblicazione: (2026)

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

Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees
di: Deng, Yuyang, et al.
Pubblicazione: (2024)

On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
di: Sahu, Sharan, et al.
Pubblicazione: (2026)

LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport
di: Shahbazi, Ashkan, et al.
Pubblicazione: (2025)

Decentralized Proximal Stochastic Gradient Langevin Dynamics
di: Islam, Mohammad Rafiqul, et al.
Pubblicazione: (2026)

Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
di: Zhang, Chenyang, et al.
Pubblicazione: (2026)

A Stochastic Optimization Framework for Private and Fair Learning From Decentralized Data
di: Gupta, Devansh, et al.
Pubblicazione: (2024)

CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence
di: Huang, Kun, et al.
Pubblicazione: (2023)

Partially Observable Gaussian Process Network and Doubly Stochastic Variational Inference
di: Kiroriwal, Saksham, et al.
Pubblicazione: (2025)