2 papers
math.OC2024
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
Anton Rodomanov, Xiaowen Jiang, Sebastian Stich
We present adaptive gradient methods (both basic and accelerated) for solving convex composite optimization problems in which the main part is approximately smooth (a.k.a. …
cs.LG2024
Federated Optimization with Doubly Regularized Drift Correction
Xiaowen Jiang, Anton Rodomanov, Sebastian U. Stich
Federated learning is a distributed optimization paradigm that allows training machine learning models across decentralized devices while keeping the data localized. The standard m…