I am a final-year CS PhD student at the University of Wisconsin-Madison, advised by Somesh Jha. In the past, I was advised by Ben Liblit. I am affliated with the fantasitic madPL group. I have also been fortunately mentored by Thomas Reps, Aws Albarghouthi and Yudong Chen.
My research lies at the intersection of programming languages and deep learning. It stems from formalizing the computational phonomena in deep learning (We CS folks call formalizing abstracting; physicists would call it modeling), with an emphasis on analyzing the variational properties of neural networks. My research style is greatly influenced by Immanuel Kant and the classical Göttingen school of mathematicians. Currently, I am very interested in nonlinear algebra.
I studied mathematics and philosophy at the University of Illinois Urbana-Champaign as an undergraduate. I also completed a master degree in computer science at the Courant Institute, New York University, before moving to Madison. At New York University, my research advisor was Richard Cole.
The best way to reach me is my email: “MyInitials (two letters) at cs.wisc.edu” (for example, pl@cs.wisc.edu).
Publications and manuscripts
Zi Wang, Jihye Choi, Ke Wang and Somesh Jha. Rethinking Diversity in Deep Neural Network Testing. Under Review
Zi Wang, Somesh Jha and Krishnamurthy (Dj) Dvijotham. Algebraic Neural-network Analysis. Under Review
Zi Wang, Aaron Havens, Alexandre Araujo, Yang Zheng, Bin Hu, Yudong Chen and Somesh Jha. On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks. ICLR 2024
Zi Wang, Gautam Prakriya and Somesh Jha. A Quantitative Geometric Approach to Neural Network Smoothness. NeurIPS 2022
Zi Wang, Aws Albarghouthi, Gautam Prakriya and Somesh Jha. Interval Universal Approximation for Neural Networks. POPL 2022
Jordan Henkel, Goutham Ramakrishnan, Zi Wang, Aws Albarghouthi, Somesh Jha and Thomas Reps. Semantic Robustness of Models of Source Code. SANER 2022
Thomas K. Panum, Zi Wang, Pengyu Kan, Earlence Fernandes and Somesh Jha. Exploring Adversarial Robustness of Deep Metric Learning. arXiv preprint arXiv:2102.07265
Zi Wang, Ben Liblit and Thomas Reps. TOFU: Target-Oriented FUzzer. arXiv preprint arXiv:2004.14375
Zi Wang. A New Strongly Polynomial Algorithm for Computing Fisher Market Equilibria with Spending Constraint Utilities. Master Thesis
Miscellaneous
My recent favorite album is RENAISSANCE. Great ideas will come back again and again 🫡.
My MOST favorite movie is Life of Pi. Life is full of metaphors, and the prototypes underneath the metaphors are the innate abstractions of the world.