no code implementations • 10 Apr 2024 • Shreyas Chaudhari, Srinivasa Pranav, José M. F. Moura
Our analysis leads to two distinct GradNet architectures, GradNet-C and GradNet-M, and we describe the corresponding monotone versions, mGradNet-C and mGradNet-M. Our empirical results show that these architectures offer efficient parameterizations and outperform popular methods in gradient field learning tasks.
no code implementations • 21 Dec 2023 • Srinivasa Pranav, José M. F. Moura
Peer-to-peer deep learning algorithms are enabling distributed edge devices to collaboratively train deep neural networks without exchanging raw training data or relying on a central server.
no code implementations • 29 Oct 2023 • Srinivasa Pranav, José M. F. Moura
We present P2PL, a practical multi-device peer-to-peer deep learning algorithm that, unlike the federated learning paradigm, does not require coordination from edge servers or the cloud.
no code implementations • 25 Jan 2023 • Shreyas Chaudhari, Srinivasa Pranav, José M. F. Moura
While much effort has been devoted to deriving and analyzing effective convex formulations of signal processing problems, the gradients of convex functions also have critical applications ranging from gradient-based optimization to optimal transport.