6.9k citations
- Meta (United Kingdom)GB158 papers
- Meta (Israel)IL62 papers
- Menlo SchoolUS51 papers
- New York UniversityUS49 papers
- Carnegie Mellon UniversityUS33 papers
- University of California, BerkeleyUS31 papers
- The University of Texas at AustinUS28 papers
- Google (United States)US27 papers
- Georgia Institute of TechnologyUS26 papers
- Stanford UniversityUS25 papers
- Cornell UniversityUS24 papers
- University of WashingtonUS20 papers
10 papers · 2 filters
Rotting bandits are not harder than stochastic ones
Julien Seznec, Andrea Locatelli, Alexandra Carpentier +2
In stochastic multi-armed bandits, the reward distribution of each arm is assumed to be stationary. This assumption is often violated in practice (e.g., in recommendation systems),…
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…
Canonical Tensor Decomposition for Knowledge Base Completion
Timothée Lacroix, Nicolas Usunier, Guillaume Obozinski
The problem of Knowledge Base Completion can be framed as a 3rd-order binary tensor completion problem. In this light, the Canonical Tensor Decomposition (CP) (Hitchcock, 1927) see…
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…
Spreading vectors for similarity search
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid +1
Discretizing multi-dimensional data distributions is a fundamental step of modern indexing methods. State-of-the-art techniques learn parameters of quantizers on training data for…
Comparing Dynamics: Deep Neural Networks versus Glassy Systems
M. Baity-Jesi, L. Sagun, M. Geiger +6
We analyze numerically the training dynamics of deep neural networks (DNN) by using methods developed in statistical physics of glassy systems. The two main issues we address are (…