Row-Stochastic Matrices Can Provably Outperform Doubly Stochastic Matrices in Decentralized Learning
Fuente:
arXiv
Saved in:
| Main Authors: | Liu, Bing, Kong, Boao, Lu, Limin, Yuan, Kun, Zhao, Chengcheng |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes
by: Kong, Boao, et al.
Published: (2026)
by: Kong, Boao, et al.
Published: (2026)
Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks
by: Hu, Zhaobo, et al.
Published: (2026)
by: Hu, Zhaobo, et al.
Published: (2026)
Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity
by: Kong, Boao, et al.
Published: (2024)
by: Kong, Boao, et al.
Published: (2024)
SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
by: Zhu, Shuchen, et al.
Published: (2024)
by: Zhu, Shuchen, et al.
Published: (2024)
Doubly Stochastic Matrices and Modified Laplacian Matrices of Graphs
by: Andrade, Enide, et al.
Published: (2025)
by: Andrade, Enide, et al.
Published: (2025)
DRACO: Decentralized Asynchronous Federated Learning over Row-Stochastic Wireless Networks
by: Jeong, Eunjeong, et al.
Published: (2024)
by: Jeong, Eunjeong, et al.
Published: (2024)
CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure
by: Kong, Boao, et al.
Published: (2025)
by: Kong, Boao, et al.
Published: (2025)
Synergistic Intra- and Cross-Layer Regularization Losses for MoE Expert Specialization
by: Hu, Rizhen, et al.
Published: (2026)
by: Hu, Rizhen, et al.
Published: (2026)
Doubly Stochastic Adaptive Neighbors Clustering via the Marcus Mapping
by: Yuan, Jinghui, et al.
Published: (2024)
by: Yuan, Jinghui, et al.
Published: (2024)
Demystifying SGD with Doubly Stochastic Gradients
by: Kim, Kyurae, et al.
Published: (2024)
by: Kim, Kyurae, et al.
Published: (2024)
PDSL: Privacy-Preserved Decentralized Stochastic Learning with Heterogeneous Data Distribution
by: Wang, Lina, et al.
Published: (2025)
by: Wang, Lina, et al.
Published: (2025)
ESPFormer: Doubly-Stochastic Attention with Expected Sliced Transport Plans
by: Shahbazi, Ashkan, et al.
Published: (2025)
by: Shahbazi, Ashkan, et al.
Published: (2025)
Armijo Line-search Can Make (Stochastic) Gradient Descent Provably Faster
by: Vaswani, Sharan, et al.
Published: (2025)
by: Vaswani, Sharan, et al.
Published: (2025)
The Homogeneity Trap: Spectral Collapse in Doubly-Stochastic Deep Networks
by: Liu, Yizhi
Published: (2026)
by: Liu, Yizhi
Published: (2026)
Doubly Stochastic Mean-Shift Clustering
by: Trigano, Tom, et al.
Published: (2026)
by: Trigano, Tom, et al.
Published: (2026)
Learning Symmetries via Weight-Sharing with Doubly Stochastic Tensors
by: van der Linden, Putri A., et al.
Published: (2024)
by: van der Linden, Putri A., et al.
Published: (2024)
BROS: Bias-Corrected Randomized Subspaces for Memory-Efficient Single-Loop Bilevel Optimization
by: Zhang, Hengrui, et al.
Published: (2026)
by: Zhang, Hengrui, et al.
Published: (2026)
Stochastic Rounding Implicitly Regularizes Tall-and-Thin Matrices
by: Dexter, Gregory, et al.
Published: (2024)
by: Dexter, Gregory, et al.
Published: (2024)
MARS-M: When Variance Reduction Meets Matrices
by: Liu, Yifeng, et al.
Published: (2025)
by: Liu, Yifeng, et al.
Published: (2025)
Provably Safe Reinforcement Learning for Stochastic Reach-Avoid Problems with Entropy Regularization
by: Mazumdar, Abhijit, et al.
Published: (2026)
by: Mazumdar, Abhijit, et al.
Published: (2026)
Decentralized Optimization over Time-Varying Row-Stochastic Digraphs
by: Liang, Liyuan, et al.
Published: (2025)
by: Liang, Liyuan, et al.
Published: (2025)
Stochastic Trace Optimization of Parameter Dependent Matrices Based on Statistical Learning Theory
by: Saibaba, Arvind K., et al.
Published: (2025)
by: Saibaba, Arvind K., et al.
Published: (2025)
Quantum Doubly Stochastic Transformers
by: Born, Jannis, et al.
Published: (2025)
by: Born, Jannis, et al.
Published: (2025)
ASAP: Amortized Doubly-Stochastic Attention via Sliced Dual Projection
by: Tran, Huy, et al.
Published: (2026)
by: Tran, Huy, et al.
Published: (2026)
A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schrödinger Equations
by: Cole, Frank, et al.
Published: (2026)
by: Cole, Frank, et al.
Published: (2026)
Stochastic Runge-Kutta Methods: Provable Acceleration of Diffusion Models
by: Wu, Yuchen, et al.
Published: (2024)
by: Wu, Yuchen, et al.
Published: (2024)
Enhancing Parallelism in Decentralized Stochastic Convex Optimization
by: Eisen, Ofri, et al.
Published: (2025)
by: Eisen, Ofri, et al.
Published: (2025)
Clapping: Removing Per-sample Storage for Pipeline Parallel Distributed Optimization with Communication Compression
by: Kong, Boao, et al.
Published: (2025)
by: Kong, Boao, et al.
Published: (2025)
Adjacent Leader Decentralized Stochastic Gradient Descent
by: He, Haoze, et al.
Published: (2024)
by: He, Haoze, et al.
Published: (2024)
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Stochastic Approach
by: Fernando, Heshan, et al.
Published: (2022)
by: Fernando, Heshan, et al.
Published: (2022)
Learning Fill-in Reduction Ordering via Graph Policy Optimization for Sparse Matrices
by: Li, Ziwei, et al.
Published: (2026)
by: Li, Ziwei, et al.
Published: (2026)
Towards Faster Decentralized Stochastic Optimization with Communication Compression
by: Islamov, Rustem, et al.
Published: (2024)
by: Islamov, Rustem, et al.
Published: (2024)
Stochastic Compositional Minimax Optimization with Provable Convergence Guarantees
by: Deng, Yuyang, et al.
Published: (2024)
by: Deng, Yuyang, et al.
Published: (2024)
On the Provable Suboptimality of Momentum SGD in Nonstationary Stochastic Optimization
by: Sahu, Sharan, et al.
Published: (2026)
by: Sahu, Sharan, et al.
Published: (2026)
LOTFormer: Doubly-Stochastic Linear Attention via Low-Rank Optimal Transport
by: Shahbazi, Ashkan, et al.
Published: (2025)
by: Shahbazi, Ashkan, et al.
Published: (2025)
Decentralized Proximal Stochastic Gradient Langevin Dynamics
by: Islam, Mohammad Rafiqul, et al.
Published: (2026)
by: Islam, Mohammad Rafiqul, et al.
Published: (2026)
Transformers Trained via Gradient Descent Can Provably Learn a Class of Teacher Models
by: Zhang, Chenyang, et al.
Published: (2026)
by: Zhang, Chenyang, et al.
Published: (2026)
A Stochastic Optimization Framework for Private and Fair Learning From Decentralized Data
by: Gupta, Devansh, et al.
Published: (2024)
by: Gupta, Devansh, et al.
Published: (2024)
CEDAS: A Compressed Decentralized Stochastic Gradient Method with Improved Convergence
by: Huang, Kun, et al.
Published: (2023)
by: Huang, Kun, et al.
Published: (2023)
Partially Observable Gaussian Process Network and Doubly Stochastic Variational Inference
by: Kiroriwal, Saksham, et al.
Published: (2025)
by: Kiroriwal, Saksham, et al.
Published: (2025)
Similar Items
-
On the Convergence of Stochastic Gradient Descent with Perturbed Forward-Backward Passes
by: Kong, Boao, et al.
Published: (2026) -
Beyond the Laplacian: Doubly Stochastic Matrices for Graph Neural Networks
by: Hu, Zhaobo, et al.
Published: (2026) -
Decentralized Bilevel Optimization: A Perspective from Transient Iteration Complexity
by: Kong, Boao, et al.
Published: (2024) -
SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
by: Zhu, Shuchen, et al.
Published: (2024) -
Doubly Stochastic Matrices and Modified Laplacian Matrices of Graphs
by: Andrade, Enide, et al.
Published: (2025)