527 citations · 1.7k across the 34 of their papers we have counts for
5 papers · 1 filter
Deep Learning at 15PF: Supervised and Semi-Supervised Classification for Scientific Data
Thorsten Kurth, Jian Zhang, Nadathur Satish +12
This paper presents the first, 15-PetaFLOP Deep Learning system for solving scientific pattern classification problems on contemporary HPC architectures. We develop supervised conv…
Improving Gibbs Sampler Scan Quality with DoGS
Ioannis Mitliagkas, Lester Mackey
The pairwise influence matrix of Dobrushin has long been used as an analytical tool to bound the rate of convergence of Gibbs sampling. In this work, we use Dobrushin influence as…
Accelerated Stochastic Power Iteration
Christopher De Sa, Bryan He, Ioannis Mitliagkas +2
Principal component analysis (PCA) is one of the most powerful tools in machine learning. The simplest method for PCA, the power iteration, requires full-data pas…
Learning Representations and Generative Models for 3D Point Clouds
Panos Achlioptas, Olga Diamanti, Ioannis Mitliagkas +1
Three-dimensional geometric data offer an excellent domain for studying representation learning and generative modeling. In this paper, we look at geometric data represented as poi…
YellowFin and the Art of Momentum Tuning
Jian Zhang, Ioannis Mitliagkas
Hyperparameter tuning is one of the most time-consuming workloads in deep learning. State-of-the-art optimizers, such as AdaGrad, RMSProp and Adam, reduce this labor by adaptively…