Hello! I am a 4th-year Electrical and Systems Engineering PhD student in the GRASP lab at the University of Pennsylvania. I am fortunate to be advised by Prof. Nikolai Matni. Previously, I graduated with BSc degrees in Mathematics and in Statistics & Data Science from Yale University. I then spent a year as a researcher in the Kluger Lab at Yale University's Applied Mathematics Program. During the summer of 2023, I interned at Microsoft Research NYC.

I am interested in:

- Learning, (for) Dynamical Systems, (and) Control.

Email: ttz2 AT seas DOT upenn DOT edu.

- Regret Analysis of Multi-task Representation Learning for Linear-Quadratic Adaptive Control, submitted. [arxiv]
- Guarantees for Nonlinear Representation Learning: Non-identical Covariates, Dependent Data, Fewer Samples, to appear at ICML 2024. [OpenReview]
- Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data, ICLR 2024. (Spotlight presentation!). [arxiv]
- Performance-Robustness Tradeoffs in Adversarially Robust Control and Estimation, accepted to IEEE Transactions on Automatic Control. [arxiv]
- Multi-Task Imitation Learning for Linear Dynamical Systems, L4DC 2023. [arxiv]
- TaSIL: Taylor Series Imitation Learning, NeurIPS 2022. [arxiv]
- Performance-Robustness Tradeoffs in Adversarially Robust Linear-Quadratic Control, CDC 2022. [arxiv]
- Adversarially Robust Stability Certificates can be Sample-Efficient, L4DC 2022. [arxiv]
- Adversarial Tradeoffs in Robust State Estimation, ACC 2023. [arxiv]
- Biwhitening Reveals the Rank of a Count Matrix, SIAM Journal on Mathematics of Data Science. [arxiv]
- Sparse Optimization on General Atomic Sets: Greedy and Forward-Backward Algorithms, pre-print. [arxiv]
- On the Continuous Fermat-Weber Problem for a Convex Polygon using Euclidean Distance. [arxiv]

- Senior project in discrepancy theory. A short summary of some results.
- Final project in SDS430 Optimization Techniques: Nesterov acceleration: higher-order methods.
- Reproducing kernel Hilbert spaces.
- A brief introduction to: Kronecker products, non-negative matrices.