Enzo Di Pasquale

Ph.D. Candidate in Economics
New York University

Welcome!

I am a Ph.D. candidate in Economics at New York University. I am mainly interested in econometrics, industrial organization, and market design.

My research focuses on estimation and optimization methods for demand, pricing, and allocation in complex markets.

Before NYU, I earned a B.Sc. and an M.Sc. in Economics from Bocconi University.

Enzo Di Pasquale

Research

Estimating Random Utility Models over Bundles with Large-Scale Linear Programming

Job market paper

Abstract

This paper develops a simulation-based estimator for random utility models over combinatorial choice sets. When utility is linear in parameters, minimizing the average regret—the difference in utility between the observed choice and the optimal alternative under simulated shocks—yields a convex objective function. Convexity overcomes the computational hurdles of the standard simulated method of moments, enabling the estimation of high-dimensional parameter vectors such as item fixed effects and complementarities. I recast the sample objective as a linear program and solve it via constraint generation. In the numerical experiments, constraint generation terminates in far fewer iterations than worst-case convex optimization benchmarks. I establish formal consistency and asymptotic normality in the standard many-observation limit, with the number of choices and parameters fixed. I then use numerical experiments to demonstrate the method's scalability to single-profile large combinatorial objects, such as supermodular potential games. Finally, I apply the framework to the 1996 FCC C-Block spectrum auction. After estimating geographic complementarities and license-specific fixed effects from the realized allocation, I evaluate counterfactual bundling policies where licenses are aggregated into a coarser geographical partition, finding that it would have lowered both seller revenue and bidder surplus.

Draft Code

Auction Algorithms for Demand Inversion with Nonlinear Transfers

Abstract

Inverting demand in random utility models with non-additive utility is equivalent to computing stable outcomes of a two-sided matching market with imperfectly transferable utility. This project develops auction algorithms for that computation. The classical auction algorithm for the assignment problem relies on a common unit of transfer: raising the price of a product lowers every consumer's payoff from it by the same amount. With nonlinear transfers, arising for instance from progressive taxation or risk aversion, the effect of a price change varies across consumer–product pairs, and the classical bidding step no longer applies. I propose a forward–reverse ε-scaling auction that handles this case, study its computational complexity, and implement it for batches of markets on GPUs and across distributed processes. In numerical experiments, I use the algorithms to invert demand with non-additive valuations and document accuracy and running time as markets grow large.

Code

Vanishing Perturbations and Rent Selection in Nonlinear Matching Markets

with Alfred Galichon and Antoine Jacquet

Abstract

Matching markets with imperfectly transferable utility can admit multiple equilibrium divisions of surplus. We study selection by exponential regularization, which assigns positive mass to every allowed match and to remaining single. Under continuity, strict monotonicity, and coercivity assumptions, payoffs converge to a uniquely selected equilibrium vector. We characterize this limit using market clearing within submarkets with equal worker and firm populations. Matches whose masses vanish with the perturbation can nevertheless determine the limiting rents. The characterization recovers the payoff selection associated with entropic optimal transport under transferable utility and applies to nonlinear transfers. Under differentiability and positive partial derivatives, we also characterize the first-order change in payoffs as the perturbation vanishes, which determines the limiting allocation.

Software

combRUM

Open-source Python library for high-dimensional estimation and bootstrap inference in combinatorial random utility models. It handles constraint generation and runs both estimation and bootstrap across MPI processes or compute nodes, with HiGHS and Gurobi backends.

Ubiquitous: Dynamic Games Between Python Strategies

with Alfred Galichon and Antoine Jacquet

A platform for running dynamic games between autonomous Python strategies. A researcher specifies the game, players submit code, and the server runs the rounds, computes payoffs, and records the full history as a panel dataset of strategic behavior.

Teaching

CV

Download my CV.

Contacts

Address: NYU Department of Economics, 19 W. 4th Street (6th Floor), New York, NY, 10012, USA.

E-mail: ed2189 [at] nyu.edu