Derivative-Informed Operator Learning for Finance: On-the-Fly Greeks, Surfaces, Hedging, and Control

By Miquel Noguer i Alonso

Published 2026-06-04

Everscope rating

1856.7

Relevance to quantitative trading

9 / 10

Implementation complexity

7 / 10

Reproducibility

4 / 5

About this paper

Methodology: On-the-Fly Derivative-Informed Operator Learning (DIF). Problem types: Regression, Optimization, Risk Management, Portfolio Optimization, Structured Prediction, Operator Learning (function-to-function mapping), PDE-constrained Optimization, Calibration (inverse problem), Hedging, Stress Testing, XVA Computation.

arXiv:2606.05900 · Paper rankings

Open the interactive Everscope explorer for full analysis, charts, and paper battles.