4.7k citations · 5.8k across the 13 of their papers we have counts for
14 papers
Variance Reduction in Deep Learning: More Momentum is All You Need
Lionel Tondji, Sergii Kashubin, Moustapha Cisse
Variance reduction (VR) techniques have contributed significantly to accelerating learning with massive datasets in the smooth and strongly convex setting (Schmidt et al., 2017; Jo…
Fairness with Overlapping Groups
Forest Yang, Moustapha Cisse, Sanmi Koyejo
In algorithmically fair prediction problems, a standard goal is to ensure the equality of fairness metrics across multiple overlapping groups simultaneously. We reconsider this sta…
On Mixup Regularization
Luigi Carratino, Moustapha Cissé, Rodolphe Jenatton +1
Mixup is a data augmentation technique that creates new examples as convex combinations of training points and labels. This simple technique has empirically shown to improve the ac…
Fooling End-to-end Speaker Verification by Adversarial Examples
Felix Kreuk, Yossi Adi, Moustapha Cisse +1
Automatic speaker verification systems are increasingly used as the primary means to authenticate costumers. Recently, it has been proposed to train speaker verification systems us…
Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
Yossi Adi, Carsten Baum, Moustapha Cisse +2
Deep Neural Networks have recently gained lots of success after enabling several breakthroughs in notoriously challenging problems. Training these networks is computationally expen…
Unbounded cache model for online language modeling with open vocabulary
Edouard Grave, Moustapha Cisse, Armand Joulin
Recently, continuous cache models were proposed as extensions to recurrent neural network language models, to adapt their predictions to local changes in the data distribution. The…
ConvNets and ImageNet Beyond Accuracy: Understanding Mistakes and Uncovering Biases
Pierre Stock, Moustapha Cisse
ConvNets and Imagenet have driven the recent success of deep learning for image classification. However, the marked slowdown in performance improvement combined with the lack of ro…
Countering Adversarial Images using Input Transformations
Chuan Guo, Mayank Rana, Moustapha Cisse +1
This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system. Spe…
mixup: Beyond Empirical Risk Minimization
Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin +1
Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple le…
Houdini: Fooling Deep Structured Prediction Models
Moustapha Cisse, Yossi Adi, Natalia Neverova +1
Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines. So far, most existing methods only work for classification and…
Parseval Networks: Improving Robustness to Adversarial Examples
Moustapha Cisse, Piotr Bojanowski, Edouard Grave +2
We introduce Parseval networks, a form of deep neural networks in which the Lipschitz constant of linear, convolutional and aggregation layers is constrained to be smaller than 1.…
Kronecker Recurrent Units
Cijo Jose, Moustpaha Cisse, Francois Fleuret
Our work addresses two important issues with recurrent neural networks: (1) they are over-parameterized, and (2) the recurrence matrix is ill-conditioned. The former increases the…
Efficient softmax approximation for GPUs
Edouard Grave, Armand Joulin, Moustapha Cissé +2
We propose an approximate strategy to efficiently train neural network based language models over very large vocabularies. Our approach, called adaptive softmax, circumvents the li…
Deep Self-Taught Learning for Handwritten Character Recognition
Frédéric Bastien, Yoshua Bengio, Arnaud Bergeron +14
Recent theoretical and empirical work in statistical machine learning has demonstrated the importance of learning algorithms for deep architectures, i.e., function classes obtained…