activity
20182021
most citedUnderstanding Unintended Memorization in Federated Learning

19 citations · 47 across the 5 of their papers we have counts for

collaborators

8 papers

cs.LG20219 cited

Revealing and Protecting Labels in Distributed Training

Trung Dang, Om Thakkar, Swaroop Ramaswamy +3

Distributed learning paradigms such as federated learning often involve transmission of model updates, or gradients, over a network, thereby avoiding transmission of private data.…

cs.CL20211 cited

A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It

Trung Dang, Om Thakkar, Swaroop Ramaswamy +3

End-to-end Automatic Speech Recognition (ASR) models are commonly trained over spoken utterances using optimization methods like Stochastic Gradient Descent (SGD). In distributed s…

cs.LG202016 cited

Training Production Language Models without Memorizing User Data

Swaroop Ramaswamy, Om Thakkar, Rajiv Mathews +3

This paper presents the first consumer-scale next-word prediction (NWP) model trained with Federated Learning (FL) while leveraging the Differentially Private Federated Averaging (…

cs.LG20202 cited

Privacy Amplification via Random Check-Ins

Borja Balle, Peter Kairouz, H. Brendan McMahan +2

Differentially Private Stochastic Gradient Descent (DP-SGD) forms a fundamental building block in many applications for learning over sensitive data. Two standard approaches, priva…

cs.LG202019 cited

Understanding Unintended Memorization in Federated Learning

Om Thakkar, Swaroop Ramaswamy, Rajiv Mathews +1

Recent works have shown that generative sequence models (e.g., language models) have a tendency to memorize rare or unique sequences in the training data. Since useful models are o…

cs.CR2020

Evading Curse of Dimensionality in Unconstrained Private GLMs via Private Gradient Descent

Shuang Song, Thomas Steinke, Om Thakkar +1

We revisit the well-studied problem of differentially private empirical risk minimization (ERM). We show that for unconstrained convex generalized linear models (GLMs), one can obt…