Portrait of William Overman

William Overman

Ph.D. Candidate, Stanford

wpo@stanford.edu

Bio

My research develops methods with formal guarantees for AI safety and alignment, especially scalable oversight: how humans can monitor, correct, and retain meaningful control over increasingly capable AI systems. Recent work studies how weaker overseers can constrain stronger agents [ICML’26], how human–agent protocols can balance safety and autonomy [ICML’26], risk-controlled model alignment [NeurIPS’24, NeurIPS’25], and causal evaluation in interacting human–AI populations [TAIGR @ ICML’26]. I draw on tools from reinforcement learning, uncertainty quantification, causal inference, and game theory.

I am a Ph.D. candidate in Operations, Information, and Technology at the Stanford Graduate School of Business, advised by Mohsen Bayati. Before Stanford, I was a visiting researcher at the Institute for Basic Science in South Korea, earned an M.S. in Computer Science from UC Irvine, and completed a B.S. in Mathematics and Computer Science at Caltech.

I also work on reinforcement learning and sequential decision-making [RLC’26, ICLR’22], network experimentation [NeurIPS’24], and healthcare operations. I have also interned at Uber, applying reinforcement learning and causal inference to problems in the ridesharing and delivery marketplaces.

News

Publications

‡ equal contribution.
※ equal contribution, sole student.
† theoretical contributions co-developed with AI.

Planning Against Learning in Rank-1 Games

W Overman†

arXiv preprint arXiv:2608.18067. 2026.

arXiv

Calibrating Conservatism for Scalable Oversight

W Overman, M Bayati

ICML 2026: International Conference on Machine Learning. 2026.

Paper arXiv

The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy

W Overman, M Bayati

ICML 2026: International Conference on Machine Learning. 2026.
Early version in NeurIPS'25 Workshop: ML×OR Workshop (Spotlight Presentation).

Paper arXiv

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

W Overman, M Bayati

RLC 2026: Reinforcement Learning Conference 2026.

Paper arXiv

Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems

W Overman, S Shirani, M Bayati

Workshop on Technical AI Governance Research @ ICML 2026

Paper arXiv

Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models

W Overman, M Bayati

NeurIPS'25: Neural Information Processing Systems. 2025.

Paper arXiv

Aligning Model Properties via Conformal Risk Control

W Overman, JJ Vallon, M Bayati

NeurIPS'24: Neural Information Processing Systems. 2024.

Paper arXiv

Higher-Order Causal Message Passing for Experimentation with Complex Interference

M Bayati‡, Y Luo‡, W Overman‡, S Shirani‡, R Xiong‡

NeurIPS'24: Neural Information Processing Systems. 2024.

Paper arXiv Code

Global convergence of multi-agent policy gradient in markov potential games

S Leonardos‡, W Overman※, I Panageas‡, G Piliouras‡

ICLR'22: International Conference on Learning Representations. 2022.

Paper arXiv Code

Planning Against Learning in Rank-1 Games

W Overman†

arXiv preprint arXiv:2608.18067. 2026.

arXiv

Calibrating Conservatism for Scalable Oversight

W Overman, M Bayati

ICML 2026: International Conference on Machine Learning. 2026.

Paper arXiv

The Oversight Game: Learning to Cooperatively Balance an AI Agent's Safety and Autonomy

W Overman, M Bayati

ICML 2026: International Conference on Machine Learning. 2026.
Early version in NeurIPS'25 Workshop: ML×OR Workshop (Spotlight Presentation).

Paper arXiv

Annealed Softmax Greedy in Many-Armed Bayesian Bandits

W Overman, M Bayati

RLC 2026: Reinforcement Learning Conference 2026.

Paper arXiv

Causal Effects with Unobserved Unit Types in Interacting Human–AI Systems

W Overman, S Shirani, M Bayati

Workshop on Technical AI Governance Research @ ICML 2026

Paper arXiv

Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models

W Overman, M Bayati

NeurIPS'25: Neural Information Processing Systems. 2025.

Paper arXiv

Can We Validate Counterfactual Estimations in the Presence of General Network Interference?

S Shirani, Y Luo, W Overman, R Xiong, M Bayati

Under Review at Management Science.
Accepted for Oral Presentation at the Conference on Digital Experimentation @ MIT (CODE@MIT), 2025
Accepted for presentation at the MSOM Technology, Innovation, and Entrepreneurship SIG, 2025.

Paper arXiv Code

Occupancy Prediction with Patient Data: Evaluating Time-Series, Patient-Level Aggregation, and Deep Set Models

SH Kim‡, W Overman※, J Pauphilet‡, WC Cha

Major Revision at Manufacturing & Service Operations Management (MSOM).

Paper arXiv

Improved Regret Bound for Safe Reinforcement Learning via Tighter Cost Pessimism and Reward Optimism

K Yu, D Lee, W Overman, D Lee

RLC 2025 (Reinforcement Learning Conference).
Journal version: Reinforcement Learning Journal (2025).

Paper arXiv

On aligning prediction models with clinical experiential learning: A prostate cancer case study

JJ Vallon, W Overman, W Xu, N Panjwani, X Ling, S Vij, HP Bagshaw, ...

arXiv'25: arXiv preprint arXiv:2509.04053. 2025.

Paper arXiv

Aligning Model Properties via Conformal Risk Control

W Overman, JJ Vallon, M Bayati

NeurIPS'24: Neural Information Processing Systems. 2024.

Paper arXiv

Higher-Order Causal Message Passing for Experimentation with Complex Interference

M Bayati‡, Y Luo‡, W Overman‡, S Shirani‡, R Xiong‡

NeurIPS'24: Neural Information Processing Systems. 2024.

Paper arXiv Code

Beating price of anarchy and gradient descent without regret in potential games

I Sakos, S Leonardos, SA Stavroulakis, W Overman, I Panageas, G Piliouras

ICLR'24: International Conference on Learning Representations. 2024.

Paper arXiv

Global convergence of multi-agent policy gradient in markov potential games

S Leonardos‡, W Overman※, I Panageas‡, G Piliouras‡

ICLR'22: International Conference on Learning Representations. 2022.

Paper arXiv Code

Independent natural policy gradient always converges in markov potential games

R Fox‡, SM McAleer‡, W Overman※, I Panageas‡

AISTATS'22: Artificial Intelligence and Statistics. 2022.

Paper arXiv Code

Some Ordered Ramsey Numbers of Graphs on Four Vertices

W Overman, JF Alm, K Coffey, C Langhoff

Australasian Journal of Combinatorics, Vol 88(3), 266–281. 2024.

Paper arXiv

Vitæ

Full Resume in PDF.

Website design from Martin Saveski. Code from this GitHub repo.
William Overman
wpo@stanford.edu