Edmond Cunningham

2 accepted papers

2022

Principal Component Flows

Edmond Cunningham, Adam D Cobb, Susmit Jha

ICML 2022spotlight

Normalizing flows map an independent set of latent variables to their samples using a bijective transformation. Despite the exact correspondence between samples and latent variables, their high level relationship is not well understood. In this paper we characterize the geometric structure of flows…

Cited by 16 Source ↗PDF ↗code ↗Scholar ↗

2021

A Change of Variables Method For Rectangular Matrix-Vector Products

Edmond Cunningham, Madalina Fiterau

AISTATS 2021poster

Rectangular matrix-vector products (MVPs) are used extensively throughout machine learning and are fundamental to neural networks such as multi-layer perceptrons. However, the use of rectangular MVPs in successive normalizing flow transformations is notably missing. This paper identifies this method…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗