Search Results for author: Moustapha Cisse

Found 11 papers, 5 papers with code

Variance Reduction in Deep Learning: More Momentum is All You Need

no code implementations23 Nov 2021 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; Johnson & Zhang, 2013; Roux et al., 2012).

Data Augmentation Distributed Optimization

Fairness with Overlapping Groups

no code implementations24 Jun 2020 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.

Classification Fairness +1

Fooling End-to-end Speaker Verification by Adversarial Examples

no code implementations10 Jan 2018 Felix Kreuk, Yossi Adi, Moustapha Cisse, Joseph Keshet

We also present two black-box attacks: where the adversarial examples were generated with a system that was trained on YOHO, but the attack is on a system that was trained on NTIMIT; and when the adversarial examples were generated with a system that was trained on Mel-spectrum feature set, but the attack is on a system that was trained on MFCC.

Speaker Verification

Unbounded cache model for online language modeling with open vocabulary

2 code implementations NeurIPS 2017 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.

Language Modelling Quantization

Countering Adversarial Images using Input Transformations

1 code implementation ICLR 2018 Chuan Guo, Mayank Rana, Moustapha Cisse, Laurens van der Maaten

This paper investigates strategies that defend against adversarial-example attacks on image-classification systems by transforming the inputs before feeding them to the system.

Adversarial Defense General Classification +1

mixup: Beyond Empirical Risk Minimization

71 code implementations ICLR 2018 Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz

We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.

Domain Generalization Memorization +2

Houdini: Fooling Deep Structured Prediction Models

no code implementations17 Jul 2017 Moustapha Cisse, Yossi Adi, Natalia Neverova, Joseph Keshet

Generating adversarial examples is a critical step for evaluating and improving the robustness of learning machines.

General Classification Pose Estimation +4

Parseval Networks: Improving Robustness to Adversarial Examples

1 code implementation ICML 2017 Moustapha Cisse, Piotr Bojanowski, Edouard Grave, Yann Dauphin, Nicolas Usunier

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.

Cannot find the paper you are looking for? You can Submit a new open access paper.