English

Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration and Lower Bounds

Optimization and Control 2022-03-21 v1 Distributed, Parallel, and Cluster Computing Information Theory Machine Learning math.IT

Abstract

We consider distributed optimization methods for problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We leverage randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler resilience in asynchronous distributed systems. We derive novel approximation guarantees for classical sketching methods and establish tight concentration results that serve as both upper and lower bounds on the error. We then extend our analysis to the accuracy of parameter averaging for distributed sketches. Furthermore, we develop unbiased parameter averaging methods for randomized second order optimization for regularized problems that employ sketching of the Hessian. Existing works do not take the bias of the estimators into consideration, which limits their application to massively parallel computation. We provide closed-form formulas for regularization parameters and step sizes that provably minimize the bias for sketched Newton directions. Additionally, we demonstrate the implications of our theoretical findings via large scale experiments on a serverless cloud computing platform.

Keywords

Cite

@article{arxiv.2203.09755,
  title  = {Distributed Sketching for Randomized Optimization: Exact Characterization, Concentration and Lower Bounds},
  author = {Burak Bartan and Mert Pilanci},
  journal= {arXiv preprint arXiv:2203.09755},
  year   = {2022}
}

Comments

arXiv admin note: text overlap with arXiv:2002.06540

R2 v1 2026-06-24T10:17:58.557Z