Generalized Axiom of Revealed Preference (GARP) Fine-Tuning

Auto-generated stub. Edit this file to add more details.

A fine-tuning paradigm that integrates the Generalized Axiom of Revealed Preference (GARP) structure, derived from utility maximization theory, into time-series foundation models to improve economic forecasting by ensuring learned patterns are rationality-consistent.

Why It Matters

The paper introduces and leverages the GARP axiom, derived from economic theory, as a structural constraint for fine-tuning time-series foundation models.

Evidence

exploit Afriat’s theorem, which guarantees that demand satisfies the Generalized Axiom of Revealed Preference (GARP) if and only if it can be generated by maximizing some utility function

Related Papers

• openalex-2603.23993-garp-efm-improving-foundation-models-with-revealed-preferenc