S
Sebastian Caldas
Researcher at Carnegie Mellon University
Publications - 4
Citations - 1120
Sebastian Caldas is an academic researcher from Carnegie Mellon University. The author has contributed to research in topics: Transfer of learning & Differential privacy. The author has an hindex of 4, co-authored 4 publications receiving 573 citations.
Papers
More filters
Posted Content
LEAF: A Benchmark for Federated Settings
Sebastian Caldas,Peter Wu,Tian Li,Jakub Konečný,H. Brendan McMahan,Virginia Smith,Ameet Talwalkar +6 more
TL;DR: LEAF is proposed, a modular benchmarking framework for learning in federated settings that includes a suite of open-source federated datasets, a rigorous evaluation framework, and a set of reference implementations, all geared towards capturing the obstacles and intricacies of practical federated environments.
Posted Content
Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
TL;DR: Federated Dropout is introduced, which allows users to efficiently train locally on smaller subsets of the global model and also provides a reduction in both client-to-server communication and local computation.
Posted Content
Differentially Private Meta-Learning
TL;DR: This work conducts the first formal study of privacy in this setting and proposes a new differentially private algorithm for gradient-based parameter transfer that not only satisfies this privacy requirement but also retains provable transfer learning guarantees in convex settings.
Proceedings Article
Differentially Private Meta-Learning
TL;DR: In this article, the authors formalize the notion of task-global differential privacy as a practical relaxation of more commonly studied threat models and propose a new differentially private algorithm for gradient-based parameter transfer that not only satisfies this privacy requirement but also retains provable transfer learning guarantees in convex settings.