Learning revenue-maximizing auctions with differentiable matching

MJ Curry, U Lyi, T Goldstein… - … Conference on Artificial …, 2022‏ - proceedings.mlr.press
We propose a new architecture to approximately learn incentive compatible, revenue-
maximizing auctions from sampled valuations. Our architecture uses the Sinkhorn algorithm …

Platform Equilibrium: Analayzing Social Welfare in Online Market Places

A Eden, GQ Ma, DC Parkes - arxiv preprint arxiv:2309.08781, 2023‏ - arxiv.org
We introduce the theoretical study of a Platform Equilibrium in a market with unit-demand
buyers and unit-supply sellers. Each seller can join a platform and transact with any buyer or …

LLM-Powered Preference Elicitation in Combinatorial Assignment

E Soumalias, Y Jiang, K Zhu, M Curry… - arxiv preprint arxiv …, 2025‏ - arxiv.org
We study the potential of large language models (LLMs) as proxies for humans to simplify
preference elicitation (PE) in combinatorial assignment. While traditional PE methods rely on …

Learning strong substitutes demand via queries

E Lock, PW Goldberg, F Marmolejo-Cossío - ACM Transactions on …, 2022‏ - dl.acm.org
This article addresses the computational challenges of learning strong substitutes demand
when given access to a demand (or valuation) oracle. Strong substitutes demand …

The limits of optimal pricing in the dark

Q Dawkins, M Han, H Xu - Advances in Neural Information …, 2021‏ - proceedings.neurips.cc
A ubiquitous learning problem in today's digital market is, during repeated interactions
between a seller and a buyer, how a seller can gradually learn optimal pricing decisions …

Recovering utility

CP Chambers, F Echenique, NS Lambert - arxiv preprint arxiv …, 2023‏ - arxiv.org
We provide sufficient conditions under which a utility function may be recovered from a finite
choice experiment. Identification, as is commonly understood in decision theory, is not …

On the limitations of data‐based price discrimination

H **e, Y Zhu, D Shishkin - Theoretical Economics, 2025‏ - Wiley Online Library
The classic third degree price discrimination (3PD) model requires the knowledge of the
distribution of buyer valuations and the covariate to set the price conditioned on the …

[PDF][PDF] Designing and Analyzing Machine Learning Algorithms in the Presence of Strategic Behavior

H Zhang - 2023‏ - reports-archive.adm.cs.cmu.edu
Abstract Machine learning algorithms now play a major role in all kinds of decision-making
scenarios, such as college admissions, credit approval, and resume screening. When the …

Learning and Robustness with Applications to Mechanism Design

MJ Curry - 2022‏ - search.proquest.com
The design of economic mechanisms, especially auctions, is an increasingly important part
of the modern economy. A particularly important property for a mechanism is …

Solving product-mix markets and learning agents' preferences

E Lock - 2021‏ - ora.ox.ac.uk
This thesis addresses computational questions arising in auctions with multiple goods
available in multiple quantities, with a focus on establishing the tractability of auction …