Angela Zhou

I am a postdoc at UC Berkeley. In spring 2022, I will be a research fellow at the Simons program on causality. In summer 2022, I will start as an Assistant Professor at USC Marshall Data Sciences and Operations in Operations.

I obtained my PhD from Cornell University in Operations Research and Information Engineering working with Nathan Kallus at Cornell Tech. My work was previously supported on a NDSEG fellowship.

My research interests are broadly in statistical machine learning for data-driven decision making under uncertainty (and ambiguity), and the interplay of statistics and optimization. My dissertation work developed causal inference and machine learning as a language for prescriptive analytics, making robust recommendations for action in view of fundamental practical challenges in observational/operational data. My work emphasizes credibility as a form of reliability, developing robust inferential procedures subject to analyst-tunable violations of assumptions. I am particularly interested in the implications of real-world complex environments that realize societal impacts of machine learning, such as e-commerce, healthcare and policy, for designing inferential methods and informing prescriptive insights.

My email is angela-zhou@berkeley.edu.

CV. Scholar.

Selected publications (Full List)

Author ordering on papers is alphabetical, following Operations Research convention.
  1. Stateful Offline Contextual Policy Evaluation and Learning Kallus, Nathan, and Zhou, Angela 2021 [Abs]
  2. Minimax-Optimal Policy Learning under Unobserved Confounding Kallus, Nathan, and Zhou, Angela Management Science (Forthcoming), supersedes Neurips 2018 version 2020 [Abs] [Code] [Video]
  3. Confounding-Robust Policy Evaluation in Infinite-Horizon Reinforcement Learning Kallus, Nathan, and Zhou, Angela Neurips 2020 [Abs] [arXiv] [Code] [Video]
  4. Assessing algorithmic fairness with unobserved protected class using data combination Kallus, Nathan, Mao, Xiaojie, and Zhou, Angela Management Science (Forthcoming). A preliminary version appeared at FaCCT 2020 2019 [Abs] [arXiv] [Code] [Video]

news

Oct 16, 2021 New paper, Stateful Offline Contextual Policy Evaluation and Learning
Oct 15, 2021 Talks at INFORMS 2021, Session SD33 (in person). And Berkeley 10/29: Semi-Autonomous Systems Seminar; BLISS Seminar
Aug 1, 2021 Moving to Berkeley for postdoc. Ping if you’re around!
Jun 24, 2021 Giving a talk at Center for Causal Inference Symposium