As a research community, we are still lacking a systematic understanding of the progress on
adversarial robustness which often makes it hard to identify the most promising ideas in …

Lipschitz constrained networks have gathered considerable attention in the deep learning
community, with usages ranging from Wasserstein distance estimation to the training of …

The implicit bias of gradient-based training algorithms has been considered mostly
beneficial as it leads to trained networks that often generalize well. However, Frei et …

We study the implicit bias of optimization in robust empirical risk minimization (robust ERM)
and its connection with robust generalization. In classification settings under adversarial …

Despite their impressive performance in classification, neural networks are known to be
vulnerable to adversarial attacks. These attacks are small perturbations of the input data …

Training dataset biases are by far the most scrutinized factors when explaining algorithmic
biases of neural networks. In contrast, hyperparameters related to the neural network …

In this thesis, we study two closely related directions: robustness and generalization in
modern deep learning. Deep learning models based on empirical risk minimization are …

The Infinitesimal Calculus explores mainly two measurements: the instantaneous rates of
change and the accumulation of quantities. This work shows that scientists, engineers …