Exact Support Recovery in Federated Regression with One-shot Communication

06/22/2020
by   Adarsh Barik, et al.
0

Federated learning provides a framework to address the challenges of distributed computing, data ownership and privacy over a large number of distributed clients with low computational and communication capabilities. In this paper, we study the problem of learning the exact support of sparse linear regression in the federated learning setup. We provide a simple communication efficient algorithm which only needs one-shot communication with the centralized server to compute the exact support. Our method does not require the clients to solve any optimization problem and thus, can be run on devices with low computational capabilities. Our method is naturally robust to the problems of client failure, model poisoning and straggling clients. We formally prove that our method requires a number of samples per client that is polynomial with respect to the support size, but independent of the dimension of the problem. We require the number of distributed clients to be logarithmic in the dimension of the problem. If the predictor variables are mutually independent then the overall sample complexity matches the optimal sample complexity of the non-federated centralized setting. Furthermore, our method is easy to implement and has an overall polynomial time complexity.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/07/2019

Robust and Communication-Efficient Federated Learning from Non-IID Data

Federated Learning allows multiple parties to jointly train a deep learn...
research
06/14/2021

Federated Myopic Community Detection with One-shot Communication

In this paper, we study the problem of recovering the community structur...
research
09/18/2019

Detailed comparison of communication efficiency of split learning and federated learning

We compare communication efficiencies of two compelling distributed mach...
research
08/17/2020

Shuffled Model of Federated Learning: Privacy, Communication and Accuracy Trade-offs

We consider a distributed empirical risk minimization (ERM) optimization...
research
11/12/2020

Coded Computing for Low-Latency Federated Learning over Wireless Edge Networks

Federated learning enables training a global model from data located at ...
research
07/07/2020

Coded Computing for Federated Learning at the Edge

Federated Learning (FL) is an exciting new paradigm that enables trainin...
research
11/30/2022

Federated deep clustering with GAN-based data synthesis

Clustering has been extensively studied in centralized settings, but rel...

Please sign up or login with your details

Forgot password? Click here to reset