activity
20152021
most citedParallel SGD: When does averaging help?

78 citations · 165 across the 10 of their papers we have counts for

collaborators
Showing stat.MLShow all

5 papers · 1 filter

stat.ML2018

h-detach: Modifying the LSTM Gradient Towards Better Optimization

Devansh Arpit, Bhargav Kanuparthi, Giancarlo Kerg +3

Recurrent neural networks are known for their notorious exploding and vanishing gradient problem (EVGP). This problem becomes more evident in tasks where the information needed to…

stat.ML2018

Manifold Mixup: Better Representations by Interpolating Hidden States

Vikas Verma, Alex Lamb, Christopher Beckham +5

Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes di…

stat.ML2018

Fortified Networks: Improving the Robustness of Deep Networks by Modeling the Manifold of Hidden Representations

Alex Lamb, Jonathan Binas, Anirudh Goyal +4

Deep networks have achieved impressive results across a variety of important tasks. However a known weakness is a failure to perform well when evaluated on data which differ from t…

stat.ML20174 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.ML201678 cited

Parallel SGD: When does averaging help?

Jian Zhang, Christopher De Sa, Ioannis Mitliagkas +1

Consider a number of workers running SGD independently on the same pool of data and averaging the models every once in a while -- a common but not well understood practice. We stud…