272 citations · 2.5k across the 136 of their papers we have counts for
8 papers · 1 filter
An Evaluation of Low Overhead Time Series Preprocessing Techniques for Downstream Machine Learning
Matthew L. Weiss, Joseph McDonald, David Bestor +8
In this paper we address the application of pre-processing techniques to multi-channel time series data with varying lengths, which we refer to as the alignment problem, for downst…
Benchmarking Resource Usage for Efficient Distributed Deep Learning
Nathan C. Frey, Baolin Li, Joseph McDonald +6
Deep learning (DL) workflows demand an ever-increasing budget of compute and energy in order to achieve outsized gains. Neural architecture searches, hyperparameter sweeps, and rap…
Bringing Atomistic Deep Learning to Prime Time
Nathan C. Frey, Siddharth Samsi, Bharath Ramsundar +2
Artificial intelligence has not yet revolutionized the design of materials and molecules. In this perspective, we identify four barriers preventing the integration of atomistic dee…
Scalable Geometric Deep Learning on Molecular Graphs
Nathan C. Frey, Siddharth Samsi, Joseph McDonald +3
Deep learning in molecular and materials sciences is limited by the lack of integration between applied science, artificial intelligence, and high-performance computing. Bottleneck…
Layer-Parallel Training with GPU Concurrency of Deep Residual Neural Networks via Nonlinear Multigrid
Andrew C. Kirby, Siddharth Samsi, Michael Jones +3
A Multigrid Full Approximation Storage algorithm for solving Deep Residual Networks is developed to enable neural network parallelized layer-wise training and concurrent computatio…
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…
Sparse Deep Neural Network Exact Solutions
Jeremy Kepner, Vijay Gadepally, Hayden Jananthan +2
Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performe…
Large Enforced Sparse Non-Negative Matrix Factorization
Brendan Gavin, Vijay Gadepally, Jeremy Kepner
Non-negative matrix factorization (NMF) is a common method for generating topic models from text data. NMF is widely accepted for producing good results despite its relative simpli…