OCJan 13
Accelerated Methods with Complexity Separation Under Data Similarity for Federated Learning ProblemsDmitry Bylinkin, Sergey Skorik, Dmitriy Bystrov et al.
Heterogeneity within data distribution poses a challenge in many modern federated learning tasks. We formalize it as an optimization problem involving a computationally heavy composite under data similarity. By employing different sets of assumptions, we present several approaches to develop communication-efficient methods. An optimal algorithm is proposed for the convex case. The constructed theory is validated through a series of experiments across various problems.