Qianxiao Li

Towards Robust Neural Networks via Close-loop Control

2021 · International Conference on Learning Representations

Despite their success in massive engineering applications, deep neural networks are vulnerable to various perturbations due to their black-box nature. Recent study has shown that a deep neural network can misclassify the data even if …

A Brief Survey on the Approximation Theory for Sequence Modelling

2023 · arXiv (Cornell University)

We survey current developments in the approximation theory of sequence modelling in machine learning. Particular emphasis is placed on classifying existing results for various model architectures through the lens of classical approximation paradigms, and the …