Institution profile

Brown University

Academic institutionnorthamerica · us
Official website
Research library717linked papers
Opportunities0open roles
Selected work

Representative Papers

Policy choice in time series by empirical welfare maximization

May 08, 2022

Dynamic multivariate time series pose challenges including time-varying environments, historical dependence, dynamic causal effects, and statistical dependencies. Method: This paper proposes Time-series Empirical Welfare Maximization (T-EWM), the first extension of the empirical welfare maximization framework to dynamic time-series settings. T-EWM employs nonparametric potential outcome modeling and conditional welfare optimization to learn dynamic optimal policies. Contribution/Results: We establish theoretical guarantees, including conditional welfare consistency and a non-asymptotic upper bound on policy regret. In simulation studies and an empirical application to COVID-19 containment policy evaluation, T-EWM significantly improves policy welfare and achieves rapid regret convergence under limited samples. The framework provides a novel paradigm for dynamic decision-making that balances statistical rigor with practical feasibility.

4 citationsRead paper

Testing Mechanisms

Apr 17, 2024

This paper addresses the challenge of testing the sharp null hypothesis of *complete mediation*—that the treatment variable (D) affects the outcome (Y) exclusively through a specified mechanism (M). We propose a general nonparametric test grounded in the Local Average Treatment Effect (LATE) framework, accommodating multivalued, high-dimensional, and nonmonotonic mechanisms (M) without imposing strong assumptions (e.g., monotonicity) on (M)’s assignment mechanism. Our key contribution is the first integration of instrumental variable methods with LATE theory to construct a falsifiable test of complete mediation. When the null is rejected, the method delivers a conservative lower bound estimate of the unmediated direct effect of (D) on (Y). We validate the approach in two empirical applications, enabling rigorous statistical inference on mediation completeness and quantitative assessment of alternative (i.e., non-(M)) causal pathways.

3 citationsRead paper

Semi-Autonomous Mathematics Discovery with Gemini: A Case Study on the Erd\H{o}s Problems

Jan 29, 2026

This work proposes a semi-autonomous discovery framework that integrates artificial intelligence with human expertise to investigate 700 mathematical conjectures labeled as “open” in Bloom’s Erdős Problem Database. Leveraging the Gemini large language model for natural language reasoning and automated literature comparison as an initial screening step, candidate solutions are subsequently evaluated by domain experts for correctness and novelty. The study reveals that many problems deemed “open” stem not from intrinsic difficulty but from challenges in literature retrieval—termed “information occlusion.” Among the 13 problems successfully resolved, five yielded novel AI-generated solutions, while eight were traced to previously published results. This research represents the first large-scale demonstration of human–AI collaborative verification in mathematical conjectures and highlights the risk of “unconscious plagiarism” inherent in AI-assisted scholarly discovery.

2 citationsRead paper

Competition, Persuasion, and Search

Nov 17, 2024

This paper investigates information design in sequential search under a principal–agent framework, where the agent cannot directly observe product quality and must purchase signals from a profit-maximizing principal. Using a repeated contracting and optimal stopping game model, the analysis integrates game theory, mechanism design, and dynamic contract theory to fully characterize the equilibrium payoff set. A key contribution is the identification of a critical threshold for search cost: when costs are low, competition leaves total surplus and its allocation unchanged; when costs are high, competition reduces aggregate efficiency yet improves agent welfare—and may even incentivize a monopolist to disclose more information. Contrary to the conventional wisdom that monopoly invariably reduces efficiency, this work demonstrates a non-monotonic relationship between market structure and information provision, offering novel theoretical foundations for information economics and platform regulation.

2 citationsRead paper

Individualized Treatment Allocation in Sequential Network Games

Feb 11, 2023

This paper addresses the problem of personalized intervention allocation in sequential games to maximize equilibrium social welfare. Given that the long-term behavior of sequentially interacting agents follows a Gibbs stationary distribution, exact modeling and optimization pose both theoretical and computational challenges. To tackle this, we propose a novel optimization framework that integrates variational approximation of the Gibbs stationary distribution with greedy policy search—yielding an individualized intervention algorithm with provable welfare regret bounds. Our method unifies variational inference, stationary equilibrium analysis, and policy optimization. Empirical evaluation on Indian microfinance data demonstrates substantial improvements in social welfare; extensive simulations and real-world validation further confirm its effectiveness, robustness, and computational feasibility.

1 citations1 influentialRead paper
Recent publications

Latest Papers