---
title: MartingaleONet: Physics-Constrained Operator Learning for Real-Time Option Pricing and Volatility Calibration
url: https://www.ml-quant.com/papers/ssrn/7498326/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 7498326
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7498326
featured: 2026-09-25
citations: unknown
topic: Derivatives & Volatility
---


# MartingaleONet: Physics-Constrained Operator Learning for Real-Time Option Pricing and Volatility Calibration

A deep operator network maps volatility surfaces to option prices under the Heston model 15,000 times faster than finite-difference methods while reducing dynamic hedging variance by over 59% under transaction costs.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7498326
- Identifier: SSRN 7498326
- Released: 2026-09-21
- First featured: Quant Letter No. 132 (2026-09-25): https://www.ml-quant.com/issues/2026-09-25/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Derivatives & Volatility
- Authors: WonChan Cho

## Related

- [Deep Learning Option Pricing with Market Implied Volatility Surfaces](https://www.ml-quant.com/papers/arxiv/2509.05911/): The study introduces a deep learning framework for pricing options based on market-implied volatility surfaces, providing an efficient and scalable method that improves with more data.
- [Deep Hedging with Options Using the Implied Volatility Surface](https://www.ml-quant.com/papers/arxiv/2504.06208/): A new deep hedging framework for index option portfolios, which includes surface-informed decisions and transaction costs, has been proposed and outperforms traditional methods in both simulated and historical data from 1996 to 2020.
- [Option Pricing with Time-Varying Volatility Risk Aversion](https://www.ml-quant.com/papers/arxiv/2204.06943/): The paper presents a pricing kernel with fluctuating volatility risk aversion to account for changes in the pricing kernel's shape, showing reduced pricing errors in an empirical application to the S&P 500 index, the CBOE VIX, and option prices.
- [Neural Term Structure of Additive Process for Option Pricing](https://www.ml-quant.com/papers/arxiv/2408.01642/): The research introduces the neural term structure model for option pricing, providing benefits in creating the risk-neutral measure, pricing formula, and fitting the implied volatility surface.
- [Short-maturity asymptotics for VIX and European options in local-stochastic volatility models](https://www.ml-quant.com/papers/arxiv/2407.16813/): The article explores the derivation of short-term predictions for European and VIX option prices in local-stochastic volatility models, and tests these predictions against numerical simulations.
- [No-Arbitrage Deep Calibration for Volatility Smile and Skewness](https://www.ml-quant.com/papers/arxiv/2310.16703/): The introduction of a Derivative-Constrained Neural Network (DCNN) enhances the calibration of implied volatility surface in option prices, aiding in understanding market dynamics and risk management.