Swaroop Ramaswamy
Swaroop Ramaswamy
Verified email at
Cited by
Cited by
Federated learning for mobile keyboard prediction
A Hard, K Rao, R Mathews, S Ramaswamy, F Beaufays, S Augenstein, ...
arXiv preprint arXiv:1811.03604, 2018
Federated learning for emoji prediction in a mobile keyboard
S Ramaswamy, R Mathews, K Rao, F Beaufays
arXiv preprint arXiv:1906.04329, 2019
Generative models for effective ML on private, decentralized datasets
S Augenstein, HB McMahan, D Ramage, S Ramaswamy, P Kairouz, ...
arXiv preprint arXiv:1911.06679, 2019
Differentially private learning with adaptive clipping
G Andrew, O Thakkar, B McMahan, S Ramaswamy
Advances in Neural Information Processing Systems 34, 17455-17466, 2021
Training production language models without memorizing user data
S Ramaswamy, O Thakkar, R Mathews, G Andrew, HB McMahan, ...
arXiv preprint arXiv:2009.10031, 2020
Understanding unintended memorization in language models under federated learning
OD Thakkar, S Ramaswamy, R Mathews, F Beaufays
Proceedings of the Third Workshop on Privacy in Natural Language Processing …, 2021
Public Data-Assisted Mirror Descent for Private Model Training
E Amid, A Ganesh, R Mathews, S Ramaswamy, S Song, T Steinke, ...
International Conference on Machine Learning 2022, 2021
Revealing and protecting labels in distributed training
T Dang, O Thakkar, S Ramaswamy, R Mathews, P Chin, F Beaufays
Advances in Neural Information Processing Systems 34, 1727-1738, 2021
UserLibri: A Dataset for ASR Personalization Using Only Text
T Breiner, S Ramaswamy, E Variani, S Garg, R Mathews, KC Sim, ...
arXiv preprint arXiv:2207.00706, 2022
A method to reveal speaker identity in distributed asr training, and how to counter it
T Dang, O Thakkar, S Ramaswamy, R Mathews, P Chin, F Beaufays
ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and …, 2022
Personalizing Speech Recognition Based on User-entered Text
S Ramaswamy, T Breiner, I Pisarev, D Zivkovic, M Chen, R Mathews, ...
Leveraging Public Data in Training Neural Networks with Private Mirror Descent
OD Thakkar, E Amid, A Ganesh, R Mathews, S Ramaswamy, S Song, ...
US Patent App. 17/937,825, 2023
Ascertaining and/or mitigating extent of effective reconstruction, of predictions, from model updates transmitted in federated learning
OD Thakkar, T Dang, SI Ramaswamy, R Mathews, F Beaufays
US Patent App. 17/535,405, 2022
Mixed client-server federated learning of machine learning model (s)
F Beaufays, A Hard, SI Ramaswamy, OD Thakkar, R Mathews
US Patent App. 17/197,954, 2022
Sparse embeddings for reduced communication costs in federated learning of language models
RM Lara McConnaughey, Kaan Ege Ozgun, Andrew Hard, Swaroop Ramaswamy ...
Sparsity In Neural Networks 2021, 2021
The system can't perform the operation now. Try again later.
Articles 1–15