EconBase
← All papers

Amortized Inference for Correlated Discrete Choice Models via Equivariant Neural Networks

Easton Huch, Michael Keane

arXiv 25 Mar 2026 · Statistics — Methodology · 1 citations (OpenAlex)

arXiv:2603.24705 · PDF · DOI · OpenAlex · Extracted main text

Abstract

Discrete choice models are fundamental tools in management science, economics, and marketing for understanding and predicting decision-making. Logit-based models are dominant in applied work, largely due to their convenient closed-form expressions for choice probabilities. However, these models entail restrictive assumptions on the stochastic utility component, constraining our ability to capture realistic and theoretically grounded choice behavior$-$most notably, substitution patterns. In this work, we propose an amortized inference approach using a neural network emulator to approximate choice probabilities for general error distributions, including those with correlated errors. Our proposal includes a specialized neural network architecture and accompanying training procedures designed to respect the invariance properties of discrete choice models. We provide group-theoretic foundations for the architecture, including a proof of universal approximation given a minimal set of invariant features. Once trained, the emulator enables rapid likelihood evaluation and gradient computation. We use Sobolev training, augmenting the likelihood loss with a gradient-matching penalty so that the emulator learns both choice probabilities and their derivatives. We show that emulator-based maximum likelihood estimators are consistent and asymptotically normal under mild approximation conditions, and we provide sandwich standard errors that remain valid even with imperfect likelihood approximation. Simulations show significant gains over the GHK simulator in accuracy and speed.

Citation extraction

59
references
97
in-text mentions
59
distinct cited
2
self-citations
14,827
main-text words

appendix boundary found by appendix_command · 59% of the source is main text. Read the extracted text to check this.

Most heavily cited references

The works this paper leans on most, across its whole bibliography — not restricted to papers in our corpus. Ranked by composite intensity, which combines how often a work is mentioned, how many sections mention it, and how much of that falls in the main text rather than the appendix.

ReferenceIntensityMentionsSectionsMain text
1Zaheer, Manzil and Kottur, Satwik and Ravanbakhsh, Siamak and Poczos… (2017) Deep Sets1.00064100%
2Blum-Smith, Ben and Huang, Ningyuan (Teresa) and Cuturi, Marco and V… (2025) Functions on Symmetric Matrices and Point Clouds via Lightweight Invariant Features from Galois Theory0.9619589%
3Czarnecki, Wojciech Marian and Osindero, Simon and Jaderberg, Max an… (2017) Sobolev training for neural networks0.9416483%
4Norets, Andriy (2012) Estimation of Dynamic Discrete Choice Models Using Artificial Neural Network Approximations0.64422100%
5Singh, Amandeep and Liu, Ye and Yoganarasimhan, Hema (2023) Choice models and permutation invariance: Demand estimation in differentiated products markets0.64422100%
6Aouad, Ali and Antoine Desir (2025) Representing Random Utility Choice Models with Nueral Networks0.58531100%
7McFadden, Daniel and Train, Kenneth (2000) Mixed MNL models for discrete response0.58531100%
8Glen E. Bredon (1972) Introduction to Compact Transformation Groups0.5113233%
9Cybenko, G (1989) Approximation by Superpositions of a Sigmoidal Function0.5113233%
10Hornik, Kurt and Stinchcombe, Maxwell and White, Halbert (1989) Multilayer Feedforward Networks are Universal Approximators0.5113233%

Showing the top 10 of 59 scored citations.