1 code implementation • 19 Mar 2024 • Divyansh Jhunjhunwala, Shiqiang Wang, Gauri Joshi
Standard federated learning (FL) algorithms typically require multiple rounds of communication between the server and the clients, which has several drawbacks, including requiring constant network connectivity, repeated investment of computational resources, and susceptibility to privacy attacks.
2 code implementations • 23 Jan 2023 • Divyansh Jhunjhunwala, Shiqiang Wang, Gauri Joshi
Federated Averaging (FedAvg) remains the most popular algorithm for Federated Learning (FL) optimization due to its simple implementation, stateless nature, and privacy guarantees combined with secure aggregation.
no code implementations • 28 Jul 2022 • Divyansh Jhunjhunwala, Pranay Sharma, Aushim Nagarkatti, Gauri Joshi
To remedy this, we propose FedVARP, a novel variance reduction algorithm applied at the server that eliminates error due to partial client participation.
no code implementations • 30 May 2022 • Yae Jee Cho, Divyansh Jhunjhunwala, Tian Li, Virginia Smith, Gauri Joshi
We provide convergence guarantees for MaxFL and show that MaxFL achieves a $22$-$40\%$ and $18$-$50\%$ test accuracy improvement for the training clients and unseen clients respectively, compared to a wide range of FL modeling approaches, including those that tackle data heterogeneity, aim to incentivize clients, and learn personalized or fair models.
no code implementations • NeurIPS 2021 • Divyansh Jhunjhunwala, Ankur Mallick, Advait Gadhikar, Swanand Kadhe, Gauri Joshi
We study the problem of estimating at a central server the mean of a set of vectors distributed across several nodes (one vector per node).
no code implementations • 8 Feb 2021 • Divyansh Jhunjhunwala, Advait Gadhikar, Gauri Joshi, Yonina C. Eldar
Communication of model updates between client nodes and the central aggregating server is a major bottleneck in federated learning, especially in bandwidth-limited settings and high-dimensional models.