Research

Tractable Modeling. Tractable models are succinct representations of functions (e.g., probability mass functions) whose structure guarantees that inference tasks remain exact and efficient. Such models constitute a promising avenue towards addressing challenges in modern artificial intelligence like privacy, fairness, robustness, and interpretability. I conduct research on both the theoretical foundations of tractable models, for example studying tradeoffs in expressivity and tractability [5,6,8], and their applications, for example in discrete diffusion [7].

Statistical Election Audits. Risk-limiting audits (RLAs) are rigorous statistical procedures used to detect errors in election results. I've conducted experiments [1] to understand the behavior of existing RLAs and developed a new statistical test, PROVIDENCE [3,4], the most efficient and secure ballot polling RLA known today. PROVIDENCE has been piloted and is implemented in the most popular election audit software in the US, open source Arlo.

Publications

Also see my Google Scholar page.

1. Oliver Broadrick, Sanyam Agarwal, Guy Van den Broeck, Markus Bläser. The Limits of Tractable Marginalization. ICML, 2025. (pdf, arXiv)
2. Anji Liu, Oliver Broadrick, Mathias Niepert, Guy Van den Broeck. Discrete Copula Diffusion. ICLR, 2025. (pdf, arXiv)
3. Oliver Broadrick, William Cao, Benjie Wang, Martin Trapp, Guy Van den Broeck. Probabilistic Circuits for Cumulative Distribution Functions. TPM Workshop at UAI 2024. (pdf, arXiv)
4. Oliver Broadrick, Honghua Zhang, Guy Van den Broeck. Polynomial Semantics of Tractable Probabilistic Circuits. UAI 2024, Oral Presentation. (pdf, arXiv, talk, slides)
5. Oliver Broadrick. Risk-Limiting Audit PROVIDENCE and Round Size Considerations. MS Thesis, The George Washington University, 2023. (pdf)
6. Oliver Broadrick, Poorvi Vora, and Filip Zagórski. PROVIDENCE: a Flexible Round-by-Round Risk-Limiting Audit. USENIX Security 2023. (pdf, usenix, talk, slides, earlier arXiv version)
7. Hesham Fouad, Oliver Broadrick, Benjamin Harvey, Charles Peeke, and Bhagirath Narahari. Real-Time AI: Using AI on the Tactical Edge. Elsevier book chapter in "Putting AI in the Critical Loop: Assured Trust and Autonomy in Human-Machine Teams", invited chapter based on presentation at 2022 AAAI Spring Symposium. (link)
8. Oliver Broadrick, Sarah Morin, Grant McClearn, Neal McBurnett, Poorvi L. Vora, and Filip Zagórski. Simulations of Ballot Polling Risk-Limiting Audits. Seventh Workshop on Advances in Secure Electronic Voting, in association with Financial Cryptography 2022. (pdf, talk, slides)

Research Talks

• May 2024, "Polynomial Semantics of Tractable Probabilistic Circuits." Invited talk, SNAIL Seminar, University of São Paulo. (slides)
• August 2023, "PROVIDENCE: a Flexible Round-by-Round Risk-Limiting Audit". USENIX Security. (talk, slides)

Teaching

I love teaching. Since high school I have tutored for hundreds of hours at the high school and college level in mathematics, computer science, and physics. I have also served as a teaching assistant in the following courses.

• Algorithms and Complexity: Spring 2025 (UCLA)
• Fundamentals of Artificial Intelligence: Fall 2024 (UCLA)
• Foundations of Computing: Spring 2021, Spring 2022, Spring 2023 (GWU)
• Discrete Structures: Spring 2020, Fall 2020, Fall 2021, Fall 2022 (GWU)

Please give me anonymous feedback on my teaching.