paper-with-me

Papers

Distributed Averaging Methods for Randomized Second Order Optimization

2020-02-16 · Burak Bartan, Mert Pilanci

We consider distributed optimization problems where forming the Hessian is computationally challenging and communication is a significant bottleneck. We develop unbiased parameter averaging methods for randomized second order optimization that employ sampling and 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. We also extend the framework of second order averaging methods to introduce an unbiased distributed optimization framework for heterogeneous computing systems with varying worker resources. Additionally, we demonstrate the implications of our theoretical findings via large scale experiments performed on a serverless computing platform.

📄 PDF Abstract BibTeX arXiv:2002.06540

Code (0)

등록된 구현이 없습니다.

Tasks

Distributed Optimization

Similar Papers 제목 키워드 기반

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

2022-03-18 · Burak Bartan, Mert Pilanci

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 d…

Cloud ComputingDistributed Optimization

Distributed Sketching Methods for Privacy Preserving Regression

2020-02-16 · Burak Bartan, Mert Pilanci

In this work, we study distributed sketching methods for large scale regression problems. We leverage multiple randomized sketches for reducing the problem dimensions as well as preserving privacy and improving straggler…

Computational EfficiencyPrivacy Preservingregression

On Second-order Optimization Methods for Federated Learning

2021-09-06 · Sebastian Bischoff, Stephan Günnemann, Martin Jaggi, Sebastian U. Stich

We consider federated learning (FL), where the training data is distributed across a large number of clients. The standard optimization method in this setting is Federated Averaging (FedAvg), which performs multiple loca…

Federated LearningSpecificity

Exponentially Fast Parameter Estimation in Networks Using Distributed Dual Averaging

2013-09-10 · Shahin Shahrampour, Ali Jadbabaie

In this paper we present an optimization-based view of distributed parameter estimation and observational social learning in networks. Agents receive a sequence of random, independent and identically distributed (i.i.d.)…

parameter estimation

Debiasing Distributed Second Order Optimization with Surrogate Sketching and Scaled Regularization

2020-07-02 · NeurIPS 2020 12 · Michał Dereziński, Burak Bartan, Mert Pilanci, Michael W. Mahoney

In distributed second order optimization, a standard strategy is to average many local estimates, each of which is based on a small sketch or batch of the data. However, the local estimates on each machine are typically …

Point ProcessesSecond-order methods