I am a third-year PhD student in computer science at the University of Pennsylvania. I am fortunate to be advised by Michael Kearns, Aaron Roth, and Duncan Watts. I am currently also a visiting student researcher at the Center for Human-Compatible AI (CHAI) at UC Berkeley. I am interested in the foundations of interactive decision-making algorithms for human-AI ecosystems. I primarily focus on human-centric reinforcement learning, working at the intersection of machine learning theory, algorithmic game theory, and rl/control. I also draw on tools from computational social science to study such algorithms in real-world settings. Prior to this, I graduated from Stanford University with a B.A.S. in Mathematics and Economics (Honors). During my time there, I was lucky to work with and be advised by Matthew Jackson, Itai Ashlagi, and Alain Schläpfer. I also spent a year working in the Dynamic Stochastic General Equilibrium (DSGE) Team at the New York Federal Reserve. I am currently supported by the NSF GRFP Fellowship.

Publications

(note: in my field, authorship is primarily in alphabetical ordering ($\alpha-\beta$))

• From Dialogue to Deliberation in AI-Induced Belief Change. Joint with P. Jamie, A. Pessianzadeh, N. Sultana, J. Ruane, S. Rezapour, H. Hosseinmardi, A. Ghasemian, and D. Watts. Manuscript coming soon.
• Toward Human-AI Complementarity Across Diverse Tasks. Joint with Y. Xu, A. Dahmani, M. Blanchard, N. Dern, E. Nastase, F. Bianco, M. Pavlovic, S. Krishna, A. Singh, E. Modesitt, M. Christ, G. Molinaro, J. Pamarthi, A. Menon, and R. Jain.
• Model Agreement via Anchoring. Joint work with E. Eaton, S. Goel, M. Hussing, M. Kearns, A. Roth, and J. Sorrell $(\alpha-\beta)$. ICLR AIWILD 2026, CHAI Workshop 2026, Simons Workshop on Agency in Collaborative Learning, COLT: Main 2026.
• Multi-Objective Reinforcement Learning for Large-Scale Tote Allocation in Human-Robot Fulfillment Centers. Joint work with G. Liu, O. Gottesman, J. Durham, A. Roth, M. Kearns, and M. Caldara. NYRL.
• Oracle-Efficient Adversarial Reinforcement Learning via Max-Following. Joint work with Z. Mhammedi and T. Marinov. ICML: EXAIT 2025.
• Replicable Reinforcement Learning with Linear Function Approximation. Joint work with E. Eaton, M. Hussing, M. Kearns, A. Roth, and J. Sorrell ($\alpha-\beta$). NYRL Oral, ICLR: Main 2026.
• Boss LLM: Adaptation via No-Regret Learning. Joint work with Y. Feng, A. Khare, and N. Nguyen ($\alpha-\beta$). ICLR: SSI-FM 2025, Manuscript.
• Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces. Joint work with E. Eaton, M. Hussing, M. Kearns, A. Roth, and J. Sorrell ($\alpha-\beta$). JHU DSAI Symposium on Human-AI Alignment 2025, ICML: Main 2025.
• Oracle-Efficient Reinforcement Learning for Max Value Ensembles. Joint work with M. Hussing, M. Kearns, A. Roth, and J. Sorrell ($\alpha-\beta$). ICML: ARLET, WIML, NeurIPS: Main 2024.
• Estimating HANK for central banks. Joint work with S. Acharya, W. Chen, M. Del Negro, K. Dogra, A. Gleich, S. Goyal, E. Maitlin, D. Lee, and R. Sarfati ($\alpha-\beta$). FRB of New York Staff Report.

Talks

• Model Agreement via Anchoring; CSS Lab Showcase.
• Model Agreement via Anchoring; CHAI All-Hands Meeting.
• Oracle-Efficient Reinforcement Learning for Max Value Ensembles; RL Theory Seminar.
• Oracle-Efficient Reinforcement Learning for Max Value Ensembles; Google Research Learning Theory Group NYC.
• Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces; Johns Hopkins University Theory Seminar.

Research/Experience

• CHAI Student Researcher (Spring 2026)
• SPAR Fellow working with Rishub Jain on Human-AI Complementarity (Fall 2025)
• Amazon Robotics Research Scientist Intern (Summer 2025)
• Cooperative AI Summer School (2025)
• Women in Theory (2025)
• Advised by Matthew Jackson for my Honors Thesis, I studied the role of homophily in the malleability of social networks using techniques drawn from Mean-Field Game Theory here
• Worked on online estimation of Heterogeneous Agent New Keynesian Models (HANK) using Sequential Monte Carlo at the NY Federal Reserve. I also briefly worked on speeding up Hamiltonian Monte Carlo (HMC) to estimate medium-scale DSGE models.
• Developed an algorithm with Itai Ashlagi that matches students in the San Francisco area with schools based upon a generalized version of the Probabilistic Serial Dictatorship mechanism with distributional constraints
• Collaborating with Alain Schläpfer on Reinforcement Learning and Imitation Learning for Optimal Stopping Problems here
• Civic Digital Fellow in Research & Statistics through Coding it Forward where I worked on Imputation of Revenue for the County Business Patterns dataset for the U.S. Census Bureau

Mentorship/Involvement

• Women in Machine Learning Volunteer
• Computer and Information Science Student Seminar Co-Founder
• Computer and Information Science Theory Seminar Volunteer
• Computer and Information Science PhD Visit Day Volunteer
• Computer and Information Science PhD Mentorship Program Volunteer
• Stanford Women in Math Mentoring Member
• Stanford Undergraduate Mathematics Organization Member

Teaching

• TA for Algorithmic Game Theory (Spring 2025, Spring 2026)
• Mathematics and Economics Tutor through the Stanford Center for Teaching and Learning

Awards/Honors

• Rising Star in IOE-ISyE-MS&E
• NSF GRFP Fellow
• Phi Beta Kappa
• Graduated with Distinction (Top 15% of Undergraduate Body)
• Coleman Sellers Award

Hobbies

Outside of research, I love to play chess, juggle, and watch films!