6 papers · 1 filter
Atlas-based Manifold Representations for Interpretable Riemannian Machine Learning
Ryan A. Robinett, Sophia A. Madejski, Kyle Ruark +2
Despite the popularity of the manifold hypothesis, current manifold-learning methods do not support machine learning directly on the latent -dimensional data manifold, as they p…
Manifold learning and optimization using tangent space proxies
Ryan A. Robinett, Lorenzo Orecchia, Samantha J. Riesenfeld
We present a framework for efficiently approximating differential-geometric primitives on arbitrary manifolds via construction of an atlas graph representation, which leverages the…
GraphChallenge.org Sparse Deep Neural Network Performance
Jeremy Kepner, Simon Alford, Vijay Gadepally +5
The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches to developing new solutions for analyzing graphs and sparse data. Sparse AI analytics present unique scalabil…
RadiX-Net: Structured Sparse Matrices for Deep Neural Networks
Ryan A. Robinett, Jeremy Kepner
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sp…
Training Behavior of Sparse Neural Network Topologies
Simon Alford, Ryan Robinett, Lauren Milechin +1
Improvements in the performance of deep neural networks have often come through the design of larger and more complex networks. As a result, fast memory is a significant limiting f…
Neural Network Topologies for Sparse Training
Ryan A. Robinett, Jeremy Kepner
The sizes of deep neural networks (DNNs) are rapidly outgrowing the capacity of hardware to store and train them. Research over the past few decades has explored the prospect of sp…