Search Results for author: Aarshvi Gajjar

Found 2 papers, 0 papers with code

Active Learning for Single Neuron Models with Lipschitz Non-Linearities

no code implementations24 Oct 2022 Aarshvi Gajjar, Chinmay Hegde, Christopher Musco

Namely, we can collect samples via statistical \emph{leverage score sampling}, which has been shown to be near-optimal in other active learning scenarios.

Active Learning

Subspace Embeddings Under Nonlinear Transformations

no code implementations5 Oct 2020 Aarshvi Gajjar, Cameron Musco

We consider low-distortion embeddings for subspaces under \emph{entrywise nonlinear transformations}.

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