Fred Zhang

z0@berkeley.edu

I am a PhD student in the Theory Group at UC Berkeley, advised by Jelani Nelson. My research is broadly in algorithm design. I am particularly interested in algorithmic questions arising from high-dimensional statistics, machine learning, and processing massive data.

I was a graduate student in the Theory of Computation group at Harvard, before moving to Berkeley with my advisor. Prior to that, I received my B.S. in Computer Science and in Mathematics from Duke University, where I had the fortune of working with Rong Ge and Debmalya Panigrahi.

Publications

A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates

with Zhixian Lei, Kyle Luh and Prayaag Venkat.

Manuscript, 2019. (arXiv)

Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms

with Alexander Wei.

Manuscript, 2019.

SGD on Neural Networks Learns Functions of Increasing Complexity

with Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris, Tristan Yang, Benjamin L. Edelman and Boaz Barak.

NeurIPS '19 (Spotlight). (arXiv)

Also appears in ICML '19 Workshop on Generalization in Deep Learning

Minimum Cut and Minimum k-Cut in Hypergraphs via Branching Contractions

with Kyle Fox and Debmalya Panigrahi.

SODA '19. (slides)

Teaching

Undergraudate Teaching Assistant, Duke University

COMPSCI 330: Design and Analysis of Algorithms (Spring 16, Fall 16, Spring 17, Fall 17, Spring 18)

Notes

Mirror Descent and Online Learning (lecture note, 2019)
Tensor Networks, Matrix Product States and Density Matrix Renormalization Group (blog post at Windows on Theory, 2018)
Goodness-of-fit Testing and Structure Learning of the Ising Model (survey, 2018)
The Topological Approach Towards Graph Evasiveness (survey, 2017)

Contact

634 Soda Hall
Berkeley CA 94709

Web
Analytics