Search Results for author: Liam Madden

Found 2 papers, 0 papers with code

Memory capacity of two layer neural networks with smooth activations

no code implementations3 Aug 2023 Liam Madden, Christos Thrampoulidis

In order to analyze general activations, we derive the precise generic rank of the network's Jacobian, which can be written in terms of Hadamard powers and the Khatri-Rao product.

Optimization and Learning with Information Streams: Time-varying Algorithms and Applications

no code implementations17 Oct 2019 Emiliano Dall'Anese, Andrea Simonetto, Stephen Becker, Liam Madden

Approaches for the design of time-varying or online first-order optimization methods are discussed, with emphasis on algorithms that can handle errors in the gradient, as may arise when the gradient is estimated.

Cannot find the paper you are looking for? You can Submit a new open access paper.