Person
Fanghui Liu
Related publications (14)
Robustness in deep learning: The good (width), the bad (depth), and the ugly (initialization)
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu
We study the average robustness notion in deep neural networks in (selected) wide and narrow, deep and shallow, as well as lazy and non-lazy training settings. We prove that in the under-parameterized setting, width has a negative effect while it improves ...
2022Sound and Complete Verification of Polynomial Networks
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Elias Abad Rocamora, Mehmet Fatih Sahin
Polynomial Networks (PNs) have demonstrated promising performance on face and image recognition recently. However, robustness of PNs is unclear and thus obtaining certificates becomes imperative for enabling their adoption in real-world applications. Exist ...
2022On the Double Descent of Random Features Models Trained with SGD
We study generalization properties of random features (RF) regression in high dimensions optimized by stochastic gradient descent (SGD) in under-/overparameterized regime. In this work, we derive precise non-asymptotic error bounds of RF regression under b ...
2022Extrapolation and Spectral Bias of Neural Nets with Hadamard Product: a Polynomial Net Study
Volkan Cevher, Grigorios Chrysos, Fanghui Liu, Zhenyu Zhu, Yongtao Wu
Neural tangent kernel (NTK) is a powerful tool to analyze training dynamics of neural networks and their generalization bounds. The study on NTK has been devoted to typical neural network architectures, but it is incomplete for neural networks with Hadamar ...
2022