Timezone: »

 
Poster
BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining
Weizhe Hua · Yichi Zhang · Chuan Guo · Zhiru Zhang · G. Edward Suh

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @
in Poster Session 1 »

Neural network robustness has become a central topic in machine learning in recent years. Most training algorithms that improve the model's robustness to adversarial and common corruptions also introduce a large computational overhead, requiring as many as ten times the number of forward and backward passes in order to converge. To combat this inefficiency, we propose BulletTrain, a boundary example mining technique to drastically reduce the computational cost of robust training. Our key observation is that only a small fraction of examples are beneficial for improving robustness. BulletTrain dynamically predicts these important examples and optimizes robust training algorithms to focus on the important examples. We apply our technique to several existing robust training algorithms and achieve a 2.2x speed-up for TRADES and MART on CIFAR-10 and a 1.7x speed-up for AugMix on CIFAR-10-C and CIFAR-100-C without any reduction in clean and robust accuracy.

Keywords: Deep Learning · Machine Learning · Robustness · Adversarial Robustness and Security

Author Information

Weizhe Hua (Cornell University)
Yichi Zhang (Cornell University)
Chuan Guo (Facebook AI Research)
Zhiru Zhang (Cornell Univeristy)
G. Edward Suh (Cornell University)

More from the Same Authors