Research

Tractable Modeling. What (minimal) properties of an AI model enable provable guarantees about its behavior? I study the tradeoff in models between expressive-efficiency (size) and tractability (computational complexity of answering queries about the model), especially focused on probabilistic models tractable for the fundamental query of marginalization [5,8].

Statistical Election Audits. Previously I developed rigorous statistical procedures for auditing elections [1,3,4].

Publications

Also see my Google Scholar page.

1. Learning Tractable Distributions Of Language Model Continuations.
   Gwen Yidou-Weng, Ian Li, Anji Liu, Oliver Broadrick, Guy Van den Broeck, Benjie Wang.
   In Submission, 2025. (pdf, arXiv)
2. Bitblasting for Constrained Decorrelation in Tractable Image Modeling.
   Poorva Garg, Benjie Wang, Oliver Broadrick, Guy Van den Broeck, Todd Millstein.
   TPM Workshop at UAI 2025. (pdf)
3. The Limits of Tractable Marginalization.
   Oliver Broadrick, Sanyam Agarwal, Guy Van den Broeck, Markus Bläser.
   ICML, 2025. (pdf, arXiv)
4. Discrete Copula Diffusion.
   Anji Liu, Oliver Broadrick, Mathias Niepert, Guy Van den Broeck.
   ICLR, 2025. (pdf, arXiv)
5. Probabilistic Circuits for Cumulative Distribution Functions.
   Oliver Broadrick, William Cao, Benjie Wang, Martin Trapp, Guy Van den Broeck.
   TPM Workshop at UAI 2024. (pdf, arXiv)
6. Polynomial Semantics of Tractable Probabilistic Circuits.
   Oliver Broadrick, Honghua Zhang, Guy Van den Broeck.
   UAI 2024, Oral Presentation. (pdf, arXiv, talk, slides)
7. Risk-Limiting Audit PROVIDENCE and Round Size Considerations.
   Oliver Broadrick.
   MS Thesis, The George Washington University, 2023. (pdf)
8. PROVIDENCE: a Flexible Round-by-Round Risk-Limiting Audit.
   Oliver Broadrick, Poorvi Vora, and Filip Zagórski.
   USENIX Security 2023. (pdf, usenix, talk, slides, earlier arXiv version)
9. Real-Time AI: Using AI on the Tactical Edge.
   Hesham Fouad, Oliver Broadrick, Benjamin Harvey, Charles Peeke, and Bhagirath Narahari.
   Elsevier book chapter in "Putting AI in the Critical Loop: Assured Trust and Autonomy in Human-Machine Teams". (link)
10. Simulations of Ballot Polling Risk-Limiting Audits.
    Oliver Broadrick, Sarah Morin, Grant McClearn, Neal McBurnett, Poorvi L. Vora, and Filip Zagórski.
    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 have tutored at the high school and college level in mathematics, computer science, and physics, and I've been a teaching assistant in the following courses:

• Algorithms and Complexity: Spring 2025, Summer 2025 (UCLA)
• Fundamentals of Artificial Intelligence: Fall 2024, Fall 2025 (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.