I am a researcher in the machine learning department at NEC Labs North America. I am broadly interested in algorithm development for core ML with theoretical guarantees, and particularly interested in developing sound theory for data-centric AI.

I completed my PhD in mathematics at Stanford University in 2023, co-advised by James Zou and Lexing Ying.

I can be reached at zach at nec-labs dot com.


Publications

Monitoring AI-Modified Content at Scale [Article 1] [2] [3] [4]
Weixin Liang, Zachary Izzo, Yaohui Zhang, et al.
ICML 2024 (Oral)

Provable Membership Inference Privacy
Zachary Izzo, Jinsung Yoon, Sercan Arik, James Zou
TMLR 2024 (Workshop version: NeurIPS TSRML 2022)

Continuous-in-Time Limit for Bayesian Bandits
Yuhua Zhu, Zachary Izzo, Lexing Ying
JMLR 2023

Data-Driven Subgroup Identification for Linear Regression
Zachary Izzo, Ruishan Liu, James Zou
ICML 2023 (Workshop version: NeurIPS LMRL 2022)

How to Learn when Data Gradually Reacts to Your Model
Zachary Izzo, James Zou, Lexing Ying
AISTATS 2022 (Workshop version: ICML SRML 2021)

Dimensionality Reduction for Wasserstein Barycenter
Zachary Izzo, Sandeep Silwal, Samson Zhou
NeurIPS 2021

How to Learn when Data Reacts to Your Model: Performative Gradient Descent
Zachary Izzo, Lexing Ying, James Zou
ICML 2021

Borrowing From the Future: Addressing Double Sampling in Model-free Control
Yuhua Zhu, Zachary Izzo, Lexing Ying
MSML 2021

Approximate Data Deletion from Machine Learning Models [Article]
Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, James Zou
AISTATS 2021


Preprints/Workshop Papers

A Theoretical Study of Dataset Distillation
Zachary Izzo, James Zou
NeurIPS M3L 2023

Importance Tempering: Group Robustness for Overparameterized Models
Yiping Lu, Wenlong Ji, Zachary Izzo, Lexing Ying
Under review