33 citations · 53 across the 14 of their papers we have counts for
4 papers · 1 filter
NBCLT: Parameter-Agnostic Norm-Ball Clipped Local Training
Linxuan Pan, Shucheng Yang, Junchi Yang
Distributed learning with multiple local steps reduces communication but aggravates drift, and its practical performance often depends on carefully tuned hyperparameters under hete…
Accelerating Distributed Optimization: A Primal-Dual Perspective on Local Steps
Junchi Yang, Murat Yildirim, Qiu Feng
In distributed machine learning, efficient training across multiple agents with different data distributions poses significant challenges. Even with a centralized coordinator, curr…
Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization
Liang Zhang, Junchi Yang, Amin Karbasi +1
Algorithmic reproducibility measures the deviation in outputs of machine learning algorithms upon minor changes in the training process. Previous work suggests that first-order met…
Faster Single-loop Algorithms for Minimax Optimization without Strong Concavity
Junchi Yang, Antonio Orvieto, Aurelien Lucchi +1
Gradient descent ascent (GDA), the simplest single-loop algorithm for nonconvex minimax optimization, is widely used in practical applications such as generative adversarial networ…