no code implementations • 23 Feb 2023 • Anindya Bijoy Das, Aditya Ramamoorthy, David J. Love, Christopher G. Brinton
Federated learning (FL) is a popular technique for training a global model on data distributed across client devices.
1 code implementation • 17 Aug 2022 • Konstantinos Konstantinidis, Namrata Vaswani, Aditya Ramamoorthy
For strong attacks, we demonstrate a reduction in the fraction of distorted gradients ranging from 16%-99% as compared to the prior state-of-the-art.
no code implementations • 5 Aug 2021 • Konstantinos Konstantinidis, Aditya Ramamoorthy
We prove the Byzantine resilience and detection guarantees of Aspis under weak and strong attacks and extensively evaluate the system on various large-scale training scenarios.
1 code implementation • 10 Oct 2020 • Konstantinos Konstantinidis, Aditya Ramamoorthy
Our numerical experiments indicate over a 36% reduction on average in the fraction of corrupted gradients compared to the state of the art.
1 code implementation • 28 Feb 2020 • Praneeth Narayanamurthy, Namrata Vaswani, Aditya Ramamoorthy
In this work we study the problem of Subspace Tracking with missing data (ST-miss) and outliers (Robust ST-miss).
no code implementations • 14 Aug 2019 • Konstantinos Konstantinidis, Aditya Ramamoorthy
In this work, we show that a class of combinatorial structures called resolvable designs can be used to develop efficient coded distributed computing schemes for both the single and multiple job scenarios considered in prior work.
1 code implementation • 18 Jul 2019 • Anindya B. Das, Aditya Ramamoorthy, Namrata Vaswani
Distributed matrix computations (matrix-vector and matrix-matrix multiplications) are at the heart of several tasks within the machine learning pipeline.
Information Theory Information Theory
no code implementations • 22 Jan 2019 • Konstantinos Konstantinidis, Aditya Ramamoorthy
Many big data algorithms executed on MapReduce-like systems have a shuffle phase that often dominates the overall job execution time.
no code implementations • 6 Nov 2018 • Li Tang, Konstantinos Konstantinidis, Aditya Ramamoorthy
We demonstrate a tradeoff between the assumed absolute value bounds on the matrix entries and the recovery threshold.
no code implementations • 8 Feb 2018 • Konstantinos Konstantinidis, Aditya Ramamoorthy
Appropriate interpretation of resolvable designs can allow for the development of coded distributed computing schemes where the splitting levels are exponentially lower than prior work.
Information Theory Information Theory