Rajiv Mathews
Rajiv Mathews is a Principal Software Engineer at Google, where he works on privacy-preserving machine learning techniques, with applications in the domains of natural language, speech and mobile keyboards.
Authored Publications
Sort By
Google
Learning from straggler clients in federated learning
Ehsan Amid
Rohan Anil
Arxiv (2024) (to appear)
FEDAQT: ACCURATE QUANTIZED TRAINING WITH FEDERATED LEARNING
Renkun Ni
Yonghui Xiao
Oleg Rybakov
Phoenix Meadowlark
Tom Goldstein
2024
Mixed Federated Learning: Joint Decentralized and Centralized Learning
Karan Singhal
Satyen Kale
Arxiv (2022) (to appear)
Capitalization Normalization for Language Modeling with an Accurate and Efficient Hierarchical {RNN} Model
You-Chi Cheng
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022, {IEEE}, pp. 6097-6101
A Method to Reveal Speaker Identity in Distributed ASR Training,and How to Counter It
Trung Dang
Om Thakkar
Peter Chin
IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2022, Virtual and Singapore, 23-27 May 2022, {IEEE}, pp. 4338-4342
Extracting Targeted Training Data from ASR Models, and How to Mitigate It
Ehsan Amid
Om Thakkar
Proc. Interspeech 2022 (2022) (to appear)
Online Model Compression for Federated Learning with Large Models
Tien-Ju Yang
Yonghui (Yohu) Xiao
Giovanni Motta
(2022)
