Byzantine Resilient Non-Convex SVRG with Distributed Batch Gradient Computations

In this work, we consider the distributed stochastic optimization problem of minimizing a non-convex function \(f(x) = \mathbb{E}_{\xi \sim \mathcal{D}} f(x; \xi)\) in an adversarial setting, where the individual functions \(f(x; \xi)\) can also be potentially non-convex. We assume that at most \(\a...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2019-12
Main Authors: Khanduri, Prashant, Bulusu, Saikiran, Sharma, Pranay, Varshney, Pramod K
Format: Article
Language:English
Subjects:
Algorithms
Computational geometry
Convergence
Convexity
Nodes
Optimization
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we consider the distributed stochastic optimization problem of minimizing a non-convex function \(f(x) = \mathbb{E}_{\xi \sim \mathcal{D}} f(x; \xi)\) in an adversarial setting, where the individual functions \(f(x; \xi)\) can also be potentially non-convex. We assume that at most \(\alpha\)-fraction of a total of \(K\) nodes can be Byzantines. We propose a robust stochastic variance-reduced gradient (SVRG) like algorithm for the problem, where the batch gradients are computed at the worker nodes (WNs) and the stochastic gradients are computed at the server node (SN). For the non-convex optimization problem, we show that we need \(\tilde{O}\left( \frac{1}{\epsilon^{5/3} K^{2/3}} + \frac{\alpha^{4/3}}{\epsilon^{5/3}} \right)\) gradient computations on average at each node (SN and WNs) to reach an \(\epsilon\)-stationary point. The proposed algorithm guarantees convergence via the design of a novel Byzantine filtering rule which is independent of the problem dimension. Importantly, we capture the effect of the fraction of Byzantine nodes \(\alpha\) present in the network on the convergence performance of the algorithm.
ISSN:2331-8422