Deep Ranking with Heterogeneous Effects

TL;DR

This paper proposes a semiparametric ranking model that separates intrinsic scores from nonlinear contextual effects, using neural networks for estimation and providing theoretical guarantees.

Contribution

It introduces a novel framework combining parametric and nonparametric components with neural network approximation, along with identifiability and minimax optimality results.

Findings

Estimator exists with high probability under random design.

Achieves minimax optimal error bounds for both components.

Numerical experiments validate theoretical results.

Abstract

Classical latent-score ranking models often fail to distinguish objects' intrinsic scores from contextual effects, which are typically nonlinear and can dominate the observed outcomes. To address this, we introduce a semiparametric ranking framework in which the log-score of each object is modeled as the sum of a utility parameter and a nonparametric covariate effects. Within this framework, we establish model identifiability under mild regularity and connectivity conditions. For estimation, we approximate the covariate effects using a neural network and estimate the parameters via maximum likelihood. Under random design assumptions, we prove that the resulting estimator exists with high probability and derive non-asymptotic error bounds that achieve minimax optimality for both the parametric and nonparametric components. Numerical experiments on both synthetic data and an ATP tennis dataset are conducted to support our findings.