Generative Adversarial Regression (GAR): Learning Conditional Risk Scenarios

TL;DR

Generative Adversarial Regression (GAR) is a novel framework that learns conditional risk scenarios aligned with specific risk objectives, improving risk preservation and robustness across policies.

Contribution

GAR extends generative modeling to conditional risk scenarios using a minimax adversarial approach aligned with elicitable risk functionals.

Findings

GAR produces risk-preserving scenarios on S ext:500 data.

Outperforms unconditional and predictive baselines in risk accuracy.

Maintains stability under adversarial policy selection.

Abstract

We propose Generative Adversarial Regression (GAR), a framework for learning conditional risk scenarios through generators aligned with downstream risk objectives. GAR builds on a regression characterization of conditional risk for elicitable functionals, including quantiles, expectiles, and jointly elicitable pairs. We extend this principle from point prediction to generative modeling by training generators whose policy-induced risk matches that of real data under the same context. To ensure robustness across all policies, GAR adopts a minimax formulation in which an adversarial policy identifies worst-case discrepancies in risk evaluation while the generator adapts to eliminate them. This structure preserves alignment with the risk functional across a broad class of policies rather than a fixed, pre-specified set. We illustrate GAR through a tail-risk instantiation based on jointly elicitable $(\mathrm{VaR}, \mathrm{ES})$ objectives. Experiments on S\&P 500 data show that GAR produces scenarios that better preserve downstream risk than unconditional, econometric, and direct predictive baselines while remaining stable under adversarially selected policies.