no code implementations • 16 Nov 2022 • Shuo Liu, Nirupam Gupta, Nitin H. Vaidya
In particular, we introduce the notion of $(f, r; \epsilon)$-resilience to characterize how well the true solution is approximated in the presence of up to $f$ Byzantine faulty agents, and up to $r$ slow agents (or stragglers) -- smaller $\epsilon$ represents a better approximation.
no code implementations • 28 Jan 2021 • Nirupam Gupta, Nitin H. Vaidya
We consider the problem of Byzantine fault-tolerance in the peer-to-peer (P2P) distributed gradient-descent method -- a prominent algorithm for distributed optimization in a P2P system.
Distributed Optimization Distributed, Parallel, and Cluster Computing
no code implementations • 11 Aug 2020 • Nirupam Gupta, Shuo Liu, Nitin H. Vaidya
We show that the CGE gradient-filter guarantees fault-tolerance against a bounded fraction of Byzantine agents under standard stochastic assumptions, and is computationally simpler compared to many existing gradient-filters such as multi-KRUM, geometric median-of-means, and the spectral filters.
no code implementations • 19 Dec 2019 • Nirupam Gupta, Nitin H. Vaidya
The coding schemes use the concept of reactive redundancy for isolating Byzantine workers that eventually send faulty information.
no code implementations • 20 Mar 2019 • Nirupam Gupta, Nitin H. Vaidya
This paper considers the problem of Byzantine fault tolerance in distributed linear regression in a multi-agent system.
no code implementations • 27 Mar 2017 • Shripad Gade, Nitin H. Vaidya
This paper considers a distributed multi-agent optimization problem, with the global objective consisting of the sum of local objective functions of the agents.
no code implementations • 15 Dec 2016 • Shripad Gade, Nitin H. Vaidya
In a distributed machine learning scenario, the dataset is stored among several machines and they solve a distributed optimization problem to collectively learn the underlying model.
no code implementations • 18 Aug 2016 • Shripad Gade, Nitin H. Vaidya
We present a distributed solution to optimizing a convex function composed of several non-convex functions.
no code implementations • 12 Aug 2016 • Shripad Gade, Nitin H. Vaidya
We present an algorithm for the recently proposed multi-parameter-server architecture.
no code implementations • 28 Jun 2016 • Lili Su, Nitin H. Vaidya
This paper addresses the problem of non-Bayesian learning over multi-agent networks, where agents repeatedly collect partially informative observations about an unknown state of the world, and try to collaboratively learn the true state.