Institution profile

University of Georgia

Academic institutionnorthamerica · us
Official website
Research library672linked papers
Opportunities0open roles
Selected work

Representative Papers

Difference-in-Differences with a Continuous Treatment

Jul 06, 2021Social Science Research Network

This paper addresses three key challenges in difference-in-differences (DID) estimation under continuous treatment: (i) selection bias due to non-random treatment assignment, (ii) incomparability of treatment effects across varying intensities, and (iii) ambiguous causal interpretation of conventional two-way fixed-effects (TWFE) estimators. We propose a generalized parallel trends assumption and establish the first rigorous identification framework for continuous-treatment DID. We formally prove that TWFE estimators—even in a two-period setting—lack clear causal interpretation under continuous treatment. To overcome this, we develop a bias-corrected, group-weighted estimator grounded in treatment-effect decomposition and augmented with selection-bias sensitivity analysis. Empirically, our method substantially revises policy effect estimates derived from standard TWFE, mitigating systematic misattribution. The proposed approach provides a robust, interpretable tool for causal inference in settings involving graded or intensity-varying interventions.

214 citations14 influentialRead paper

Explicit Second-Order Min-Max Optimization Methods with Optimal Convergence Guarantee

Oct 23, 2022arXiv.org

For unconstrained convex-concave minimax optimization, this paper proposes a class of inexact regularized Newton-type algorithms that incorporate second-order information into the hypergradient framework while ensuring global convergence under inexact computations. Theoretically, it achieves the first $O(varepsilon^{-2/3})$ iteration complexity—matching the known lower bound—for such problems. Each iteration requires only one Schur decomposition and $O(loglog(1/varepsilon))$ linear solver calls, eliminating the redundant $loglog$ factor present in prior second-order methods. Through analysis based on the restricted gap function, we establish boundedness of iterates and convergence of the averaged sequence to an $varepsilon$-saddle point. Experiments on synthetic and real-world datasets demonstrate that the proposed method significantly outperforms existing second-order minimax optimization algorithms in both accuracy and efficiency.

14 citations6 influentialRead paper

Opportunities and Challenges of Large Language Models for Low-Resource Languages in Humanities Research

Nov 30, 2024arXiv.org

Low-resource languages encode vital cultural and historical knowledge yet suffer from data scarcity, inadequate model adaptation, and insufficient cultural sensitivity. To address these challenges, we propose the first large language model (LLM) application framework tailored for humanities research on low-resource languages. Our method integrates instruction fine-tuning, few-shot prompting, multilingual knowledge distillation, and cultural-context alignment, augmented by domain-specific knowledge graphs and sparse-label enhancement to enable culturally grounded fine-tuning and ethics-aware data governance. Experimental results demonstrate that our customized models achieve 32–57% accuracy improvements over baselines on three core digital humanities tasks: classical text transcription, endangered dialect analysis, and oral history structuring. As a community resource, we release LinguaHumanis v1.0—an open-source, task-diverse evaluation benchmark—providing both methodological foundations and practical implementation guidelines for low-resource language research in the digital humanities.

14 citations1 influentialRead paper

Maker-Breaker is solved in polynomial time on hypergraphs of rank 3

Sep 26, 2022

This paper investigates the winner determination problem for Maker-Breaker positional games on 3-uniform hypergraphs. While the problem is PSPACE-complete on general 5-uniform hypergraphs, polynomial-time algorithms were previously known only for two restricted subclasses; Rahman and Watson (2020) conjectured tractability for all 3-uniform hypergraphs. We confirm this conjecture by introducing a “vertex hazard” analytical framework and defining the novel notion of “hazardous subhypergraphs.” We construct a critical family ℱ of hazardous sets and establish a structural characterization: Breaker wins if and only if, at every vertex, all ℱ-hazardous sets pairwise intersect. Based on this, we design the first polynomial-time algorithm for arbitrary 3-uniform hypergraphs, reducing the complexity from PSPACE to P. Furthermore, we prove that if Maker wins, she can achieve her goal within O(log n) moves, and we correct an erroneous claim in recent literature.

7 citations1 influentialRead paper

Opinion dynamics on signed graphs and graphons: Beyond the piece-wise constant case

Apr 12, 2024IEEE Conference on Decision and Control

This paper investigates opinion dynamics in large-scale undirected networks incorporating negative interactions (e.g., repulsion, antagonism). Addressing opinion polarization on signed graphs, we rigorously extend repulsive opinion models to the graphon framework for the first time, proving existence and uniqueness of solutions to the associated continuous graphon dynamical system. We then establish a uniform approximation theory linking finite signed graphs to their graphon limit, demonstrating that the graphon model accurately captures opinion evolution on large random signed graphs. Integrating tools from graph theory, nonlinear dynamical systems, and random graph sampling—complemented by numerical simulations—we validate both the theoretical approximation accuracy and the model’s robustness against structural perturbations. The core contribution is the construction of the first provably convergent signed-graphon opinion dynamics framework, enabling rigorous analysis of polarization in large-scale antagonistic networks.

3 citationsRead paper
Recent publications

Latest Papers