2k citations · 4.8k across the 35 of their papers we have counts for
3 papers · 1 filter
On the Relation Between the Sharpest Directions of DNN Loss and the SGD Step Length
Stanisław Jastrzębski, Zachary Kenton, Nicolas Ballas +3
Stochastic Gradient Descent (SGD) based training of neural networks with a large learning rate or a small batch-size typically ends in well-generalizing, flat regions of the weight…
A Closer Look at Memorization in Deep Networks
Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas +8
We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noi…
Describing Videos by Exploiting Temporal Structure
Li Yao, Atousa Torabi, Kyunghyun Cho +4
Recent progress in using recurrent neural networks (RNNs) for image description has motivated the exploration of their application for video description. However, while images are…