Research

Publications

• Zhifeng Kong, Kamalika Chaudhuri. The Expressive Power of Planar Flows. Accepted by The Workshop on Theory of Deep Learning: Where next? [pdf] [slides] [poster] [video]

• Zhifeng Kong, Kamalika Chaudhuri. The Expressive Power of a Class of Normalizing Flow Models. Accepted by AISTATS 2020.

• Zhaoyang Lyu, Ching-Yun Ko, Zhifeng Kong, Ngai Wong, Dahua Lin, Luca Daniel. Fastened CROWN: Tightened Neural Network Robustness Certificates. Accepted by AAAI 2020. [pdf]

• Zhifeng Kong. Convergence Analysis of Training Two-hidden-layer Partially Over-parameterized ReLU Networks vis Gradient Descent. In submission.

• Xingyu Wan, Qing Zhao, Jinjun Wang, Shunming Deng, Zhifeng Kong. Multi-Object Tracking Using Online Metric Learning with Long Short-Term Memory. IEEE ICIP 2018, 788-792. [pdf]

• Lu Pengfei, Fan Ya, Zhou Linhua, Qian Jun, Liu Linna, Zhao Siyan, Zhifeng Kong. Study on Feature Extraction and Classification of Animal Blood Spectra Based on Support Vector Machine. Spectroscopy and Spectral Analysis. [pdf]

Manuscripts before coming to UCSD

• Zhifeng Kong. Convergence Analysis of the Dynamics of a Special Kind of Two-Layered Neural Networks with l1 and l2 Regularization. [arXiv]

• Zhifeng Kong, Shuo Ding. Generative Adversarial Networks with Inverse Transformation Unit. [arXiv]

• Qi Lyu, Zhifeng Kong, Chao Shen, Tianwei Yue. WristAuthen: A Dynamic Time Wrapping Approach for User Authentication by Hand-Interaction through Wrist-Worn Devices. [arXiv]

Blogs

• Generalization Theory for GANs. [slides]

• Invertible ResNets. [slides]