Search Results for author:
Found 4 papers, 2 papers with code
TART: Boosting Clean Accuracy Through Tangent Direction Guided Adversarial Training
To the best of our knowledge, our paper is the first work to consider the concept of tangent space and direction in the context of adversarial defense.
Biased Dueling Bandits with Stochastic Delayed Feedback
The second algorithm is tailored for situations where the distribution is unknown, but only the expected value of delay is available.
A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise
While existing methods address this problem in various directions, they still produce unpredictable sub-optimal results since they rely on the posterior information estimated by the feature extractor corrupted by noisy labels.
Alignment and Comparison of Directed Networks via Transition Couplings of Random Walks
Given two networks and a cost function relating their vertices, NetOTC finds a transition coupling of their associated random walks having minimum expected cost.
