I am a 3rd year CS PhD student in the Theory Group at Yale University, where I am extremely fortunate to be advised by Quanquan C. Liu. Currently, I am also a student researcher at Google Research in the NYC Algorithms & Optimization Group hosted by Vincent Cohen-Addad and Alessandro Epasto.

I am grateful to be supported by an NSERC Postgraduate Scholarship.

**Research Interests:**
I am broadly interested in the theory and practice of algorithms for large data
and different notions of algorithmic stability.
Examples include
parallel graph algorithms,
differentially private (DP) graph algorithms,
DP learning algorithms,
replicable learning algorithms,
and learning under structured biases.

**Email:** felix [dot] zhou [at] yale [dot] edu

My amazing collaborators (in no particular order): Samson Zhou, Vincent Cohen-Addad, Manolis Zampetakis, Grigoris Velegkas, Yuichi Yoshida, Tamalika Mukherjee, Alessandro Epasto, Alkis Kalavasis, Anay Mehrotra, Kasper Green Larsen, Amin Karbasi, Lin F. Yang, Vahab Mirrokni, Chaitanya Swamy, Jochen Koenemann, W. Justin Toth

**Personal:**
My other half,
Jane Shi,
studies number theory at MIT.

Previously, I was an undergraduate student at the University of Waterloo, where I was fortunate to be advised by Jochen Koenemann and Chaitanya Swamy. I worked on combinatorial optimization, approximation algorithms, and algorithmic game theory.

I interned at Hudson River Trading as an algorithm developer. Previously, I interned at HomeX, where I worked on an online stochastic reservation problem. Even earlier, I interned at the Google Mountain View office, where I worked on distributed graph algorithms.

The Power of Graph Sparsification in the Continual Release Model with Alessandro Epasto, Quanquan C. Liu, Tamalika Mukherjee [preprint] [poster]

Pointwise Lipschitz Continuous Graph Algorithms via Proximal Gradient Analysis with Quanquan C. Liu, Grigoris Velegkas, Yuichi Yoshida [preprint] [slides]

On the Computational Landscape of Replicable Learning
with Alkis Kalavasis, Amin Karbasi, Grigoris Velegkas
to appear in *NeurIPS, 2024*.
[preprint]

Replicable Learning of Large-Margin Halfspaces
with Alkis Kalavasis, Amin Karbasi, Kasper Green Larsen, Grigoris Velegkas
to appear in *ICML, 2024*.
**Spotlight**
(top 3.5% of accepted papers)
[preprint]
[slides]

Replicability in Reinforcement Learning
with Amin Karbasi, Grigoris Velegkas, Ling F. Yang
*NeurIPS, 2023*.
[preprint]
[video]

Replicable Clustering
with Hossein Esfandiari, Amin Karbasi, Vahab Mirrokni, Grigoris Velegkas
*NeurIPS, 2023*.
[preprint]
[slides]
[video]

On the Complexity of Nucleolus Computation for Bipartite b-Matching Games
with Jochen Koenemann, Justin Toth
*SAGT, 2021*.
**Special Issue**
[preprint]
[slides]
[video]

Notes typeset for courses and from self-studying. Errors are abundant. Please use at your own discretion.

- Math 627: Probability Theory
- CPSC 516: Algorithms via Convex Optimization
- Intro to Stochastic Calculus
- Intro to Manifolds
- Intro to Differential Geometry (in progress)

- Math 247: Calculus III (Advanced)
- PMath 340: Number Theory
- PMath 347: Groups & Rings
- PMath 351: Real Analysis
- PMath 450/650: Lebesgue Integration & Fourier Analysis
- PMath 453/753: Functional Analysis

- CS 246E: Object-Oriented Programming (Advanced)
- CS 341: Intro to Algorithms
- CS 350: Operating Systems
- CS 365: Models of Computation (Advanced)
- CS 466/666: Algorithm Design & Analysis
- CS 480/680: Intro to Machine Learning
- CS 467/667: Intro to Quantum Information Processing
- CS 762: Graph-Theoretic Algorithms