Fred Zhang

z0@berkeley.edu

I am a final-year CS PhD student at UC Berkeley, advised by Jelani Nelson. My research spans algorithms, machine learning and high-dimensional statisics. More recently, I am working on language model interpretability.

In Summer 2023, I interned at Google NYC, hosted by Matthew Fahrbach and Peilin Zhong. I also received mentorship from Neel Nanda. In Summer 2022, I was a research intern at Google Brain, working with Richard Zhang and David Woodruff.

Prior to graduate school, I received B.S. in Computer Science and B.S. in Mathematics from Duke University, where I had the fortune of working with Rong Ge and Debmalya Panigrahi.

Links: Resume / Google Scholar / Twitter


Publications show selected / by date / by topic

Topics: Language model interpretability / Algorithmic statistics / Sublinear algorithms / Learning-based algorithms / Others

Authorships are in alphabetical order, as is common in theoretical computer science, unless indicated otherwise.

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
Fred Zhang and Neel Nanda (contribution order).

Submitted (arXiv, Twitter thread)

Constant Approximation for Individual Preference Stable Clustering
with Anders Aamand, Justin Y. Chen, Allen Liu, Sandeep Silwal, Pattara Sukprasert and Ali Vakilian.

NeurIPS 2023  Spotlight

Streaming Algorithms for Learning with Experts: Deterministic Versus Robust
with David P. Woodruff and Samson Zhou.

NeurIPS 2023 (arXiv)

Privately Estimating a Gaussian: Efficient, Robust and Optimal
with Daniel Alabi, Pravesh K. Kothari, Pranay Tankala and Prayaag Venkat.

STOC 2023 (arXiv)

Bayesian Strategy-Proof Facility Location via Robust Estimation
with Manolis Zampetakis.

AISTATS 2023 (Paper)

Robust Algorithms on Adaptive Inputs from Bounded Adversaries
with Yeshwanth Cherapanamjeri, Sandeep Silwal, David P. Woodruff, Qiuyi Zhang and Samson Zhou.

ICLR 2023 (arXiv)

Online Prediction in Sub-linear Space
with Binghui Peng.

SODA 2023  Best Student Paper  (arXiv)

Optimal Query Complexities for Dynamic Trace Estimation
with David P. Woodruff and Qiuyi Zhang.

NeurIPS 2022 (arXiv)

Faster Fundamental Graph Algorithms via Learned Predictions
with Justin Y. Chen, Sandeep Silwal and Ali Vakilian.

ICML 2022 (arXiv)

Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization
with Samuel B. Hopkins and Jerry Li.

NeurIPS 2020 (arXiv)

Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
with Alexander Wei.

NeurIPS 2020 (arXiv)

A Fast Spectral Algorithm for Mean Estimation with Sub-Gaussian Rates
with Zhixian Lei, Kyle Luh and Prayaag Venkat.

COLT 2020 (arXiv)

SGD on Neural Networks Learns Functions of Increasing Complexity
Preetum Nakkiran, Gal Kaplun, Dimitris Kalimeris, Tristan Yang, Benjamin L. Edelman, Fred Zhang and Boaz Barak (contribution order).

NeurIPS 2019  Spotlight   (arXiv)

Minimum Cut and Minimum k-Cut in Hypergraphs via Branching Contractions
with Kyle Fox and Debmalya Panigrahi.

SODA 2019 & ACM Transactions on Algorithms (TALG) (journal version)


Notes


Teaching

Graduate Student Instructor, UC Berkeley
  • CS 294-165: Sketching Algorithms (Fall 20)
  • CS 170: Efficient Algorithms and Intractable Problems (Spring 20)
Undergraudate Teaching Assistant, Duke University

Contact

615 Soda Hall
Berkeley CA 94709