3 papers
math.OC2026
The Dual Averaging Power-Prox Method with Application to Heavy-Tail Incremental Gradient
Yuan Gao, Jeremy Rack, Sebastian U. Stich
We study finite-sum composite optimization under two departures from classical stochastic gradient descent theory that are central in practice: incremental gradient access and heav…
math.OC2025
Composite Optimization with Error Feedback: the Dual Averaging Approach
Yuan Gao, Anton Rodomanov, Jeremy Rack +1
Communication efficiency is a central challenge in distributed machine learning training, and message compression is a widely used solution. However, standard Error Feedback (EF) m…
math.OC2025
Accelerated Distributed Optimization with Compression and Error Feedback
Yuan Gao, Anton Rodomanov, Jeremy Rack +1
Modern machine learning tasks often involve massive datasets and models, necessitating distributed optimization algorithms with reduced communication overhead. Communication compre…