Matrix factorization (MF) mechanisms for differential privacy (DP) have
...
We train language models (LMs) with federated learning (FL) and differen...
We present a rigorous methodology for auditing differentially private ma...
We study (differentially) private federated learning (FL) of language mo...
As the adoption of federated learning increases for learning from sensit...
ML models are ubiquitous in real world applications and are a constant f...
Privacy auditing techniques for differentially private (DP) algorithms a...
Privacy noise may negate the benefits of using adaptive optimizers in
di...
Small on-device models have been successfully trained with user-level
di...
We introduce new differentially private (DP) mechanisms for gradient-bas...
This paper presents the first consumer-scale next-word prediction (NWP) ...
Differentially Private Stochastic Gradient Descent (DP-SGD) forms a
fund...
Federated learning is a distributed machine learning paradigm in which a...
We study local SGD (also known as parallel SGD and federated averaging),...
Federated learning (FL) is a machine learning setting where many clients...
The decentralized nature of federated learning makes detecting and defen...
To improve real-world applications of machine learning, experienced mode...
We introduce a new adaptive clipping technique for training learning mod...
We consider convex SGD updates with a block-cyclic structure, i.e. where...
Machine learning (ML) techniques are enjoying rapidly increasing adoptio...
Federated Learning is a distributed machine learning approach which enab...
Communication on heterogeneous edge networks is a fundamental bottleneck...
In this work we address the practical challenges of training machine lea...
Modern federated networks, such as those comprised of wearable devices,
...
Distributed stochastic gradient descent is an important subroutine in
di...
The recent, remarkable growth of machine learning has led to intense int...
Secure Aggregation protocols allow a collection of mutually distrust par...
Machine learning techniques based on neural networks are achieving remar...
We analyze and evaluate an online gradient descent algorithm with adapti...