527 citations · 1.7k across the 34 of their papers we have counts for
Showing 2017 · stat.MLShow all
2 papers · 2 filters
stat.ML2017★ 4 cited
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…
stat.ML2017★ 68 cited
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…