Search Results for author:
Found 10 papers, 6 papers with code
FAX: Scalable and Differentiable Federated Primitives in JAX
We show that FAX provides an easily programmable, performant, and scalable framework for federated computations in the data center.
Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy
We propose a simplified setting that distills key facets of these methods and isolates the impact of linearly correlated noise.
Federated Automatic Differentiation
We propose a federated automatic differentiation (FAD) framework that 1) enables computing derivatives of functions involving client and server computation as well as communication between them and 2) operates in a manner compatible with existing federated technology.
Multi-Epoch Matrix Factorization Mechanisms for Private Machine Learning
We formalize the problem of DP mechanisms for adaptive streams with multiple participations and introduce a non-trivial extension of online matrix factorization DP mechanisms to our setting.
Improved Differential Privacy for SGD via Optimal Private Linear Operators on Adaptive Streams
Motivated by recent applications requiring differential privacy over adaptive streams, we investigate the question of optimal instantiations of the matrix mechanism in this setting.
Iterated Vector Fields and Conservatism, with Applications to Federated Learning
In the context of federated learning, we show that when clients have loss functions whose gradients satisfy this condition, federated averaging is equivalent to gradient descent on a surrogate loss function.
Federated Reconstruction: Partially Local Federated Learning
We also describe the successful deployment of this approach at scale for federated collaborative filtering in a mobile keyboard application.
Fast Dimension Independent Private AdaGrad on Publicly Estimated Subspaces
In particular, we show that if the gradients lie in a known constant rank subspace, and assuming algorithmic access to an envelope which bounds decaying sensitivity, one can achieve faster convergence to an excess empirical risk of $\tilde O(1/\epsilon n)$, where $\epsilon$ is the privacy budget and $n$ the number of samples.
Adaptive Federated Optimization
Federated learning is a distributed machine learning paradigm in which a large number of clients coordinate with a central server to learn a model without sharing their own training data.
Improving Federated Learning Personalization via Model Agnostic Meta Learning
We present FL as a natural source of practical applications for MAML algorithms, and make the following observations.
