Hubert Eichner
YOU?
Author Swipe
View article: Federated Learning in Practice: Reflections and Projections
Federated Learning in Practice: Reflections and Projections Open
Federated Learning (FL) is a machine learning technique that enables multiple entities to collaboratively learn a shared model without exchanging their local data. Over the past decade, FL systems have achieved substantial progress, scalin…
View article: Confidential Federated Computations
Confidential Federated Computations Open
Federated Learning and Analytics (FLA) have seen widespread adoption by technology platforms for processing sensitive on-device data. However, basic FLA systems have privacy limitations: they do not necessarily require anonymization mechan…
View article: Federated Training of Dual Encoding Models on Small Non-IID Client Datasets
Federated Training of Dual Encoding Models on Small Non-IID Client Datasets Open
Dual encoding models that encode a pair of inputs are widely used for representation learning. Many approaches train dual encoding models by maximizing agreement between pairs of encodings on centralized training data. However, in many sce…
View article: A Field Guide to Federated Optimization
A Field Guide to Federated Optimization Open
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection. The distributed learning process can be formulated a…
View article: Advances and Open Problems in Federated Learning
Advances and Open Problems in Federated Learning Open
Federated learning (FL) is a machine learning setting where many clients (e.g., mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g., service provider), while keeping the tr…
View article: Federated Evaluation of On-device Personalization
Federated Evaluation of On-device Personalization Open
Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe methods to extend the federation framework to evaluate str…
View article: Federated Evaluation of On-device Personalization
Federated Evaluation of On-device Personalization Open
Federated learning is a distributed, on-device computation framework that enables training global models without exporting sensitive user data to servers. In this work, we describe methods to extend the federation framework to evaluate str…
Semi-Cyclic Stochastic Gradient Descent Open
We consider convex SGD updates with a block-cyclic structure, i.e. where each cycle consists of a small number of blocks, each with many samples from a possibly different, block-specific, distribution. This situation arises, e.g., in Feder…
View article: Towards Federated Learning at Scale: System Design
Towards Federated Learning at Scale: System Design Open
Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralized data. We have built a scalable production system for Federated Learning in the domain of mobile devices, based on…
View article: Applied Federated Learning: Improving Google Keyboard Query Suggestions
Applied Federated Learning: Improving Google Keyboard Query Suggestions Open
Federated learning is a distributed form of machine learning where both the training data and model training are decentralized. In this paper, we use federated learning in a commercial, global-scale setting to train, evaluate and deploy a …
View article: Federated Learning for Mobile Keyboard Prediction
Federated Learning for Mobile Keyboard Prediction Open
We train a recurrent neural network language model using a distributed, on-device learning framework called federated learning for the purpose of next-word prediction in a virtual keyboard for smartphones. Server-based training using stoch…
Neural mechanisms underlying sensitivity to reverse-phi motion in the fly Open
Optical illusions provide powerful tools for mapping the algorithms and circuits that underlie visual processing, revealing structure through atypical function. Of particular note in the study of motion detection has been the reverse-phi i…