Search Results for author: Susama Agarwala

Found 4 papers, 0 papers with code

Geometric instability of out of distribution data across autoencoder architecture

no code implementations28 Jan 2022 Susama Agarwala, Ben Dees, Corey Lowman

We study the map learned by a family of autoencoders trained on MNIST, and evaluated on ten different data sets created by the random selection of pixel values according to ten different distributions.

Eigenvalues of Autoencoders in Training and at Initialization

no code implementations27 Jan 2022 Benjamin Dees, Susama Agarwala, Corey Lowman

In this paper, we investigate the evolution of autoencoders near their initialization.

Geometry and Generalization: Eigenvalues as predictors of where a network will fail to generalize

no code implementations13 Jul 2021 Susama Agarwala, Benjamin Dees, Andrew Gearhart, Corey Lowman

We study the deformation of the input space by a trained autoencoder via the Jacobians of the trained weight matrices.

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