Suhas Diggavi

On Byzantine-Resilient High-Dimensional Stochastic Gradient Descent

2020

We study stochastic gradient descent (SGD) in the master-worker architecture under Byzantine attacks. Building upon the recent advances in algorithmic high-dimensional robust statistics, in each SGD iteration, master employs a non-trivial decoding to estimate the …

Renyi Differential Privacy of the Subsampled Shuffle Model in Distributed Learning

2021 · arXiv (Cornell University)

We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated learning (FL) …