Publication
Robust NAS under adversarial training: benchmark, theory, and beyond
Publications associées (36)
Understanding and Improving Fast Adversarial Training
Nicolas Henri Bernard Flammarion, Maksym Andriushchenko
A recent line of work focused on making adversarial training computationally efficient for deep learning models. In particular, Wong et al. (2020) showed that ℓ∞-adversarial training with fast gradient sign method (FGSM) can fail due to a phenomenon called ...
2020Deep Generative Models and Applications
Over the past few years, there have been fundamental breakthroughs in core problems in machine learning, largely driven by advances in deep neural networks. The amount of annotated data drastically increased and supervised deep discriminative models exceed ...
EPFL2020Supplementary Material - AL2: Progressive Activation Loss for Learning General Representations in Classification Neural Networks
Sabine Süsstrunk, Majed El Helou, Frederike Dümbgen
In this supplementary material, we present the details of the neural network architecture and training settings used in all our experiments. This holds for all experiments presented in the main paper as well as in this supplementary material. We also show ...
2020Evaluating the search phase of neural architecture search
Mathieu Salzmann, Martin Jaggi, Claudiu-Cristian Musat, Kaicheng Yu
Neural Architecture Search (NAS) aims to facilitate the design of deep networks fornew tasks. Existing techniques rely on two stages: searching over the architecture space and validating the best architecture. NAS algorithms are currently compared solely b ...
2020