← Search

Sai Aparna Aketi

2 accepted papers

2026

Efficient DP-SGD for LLMs with Randomized Clipping

ICML 2026poster

Large language models (LLMs) are trained on vast datasets that may contain sensitive information. Differential privacy (DP), the de facto standard for formal privacy guarantees, provides a principled framework for training LLMs with provable privacy protection. However, state-of-the-art DP training …

Cited by 0SourceScholar
2023

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

NeurIPS 2023poster

Decentralized learning enables the training of deep learning models over large distributed datasets generated at different locations, without the need for a central server. However, in practical scenarios, the data distribution across these devices can be significantly different, leading to a degrad…