---
title: "Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2607.27188v1"
permalink: "https://feed.astralor.com/items/itm_c3815c2f60fd93bb5c516934"
published: "2026-07-29T17:56:20.000Z"
score: 74
channel: "tech"
tags: ["DeepONet","NIFTY","SVI","Lognormal Mixture","Option Pricing","Risk-Neutral Density"]
---

# Inverse Learning of Latent Risk-Neutral Densities from Irregular Option Quotes

## AI commentary

> This paper impresses me by breaking the 'deep learning is omnipotent' illusion. In financial pricing, simple mixture models can sometimes outperform complex neural operators, depending on your objective. If you're a quant researcher, don't jump to Transformers until you have solid baselines. The numerical conditioning analysis is a must-read for anyone in AI+finance.

## At a glance

This paper investigates that accurate option prices do not guarantee accurate recovery of the latent risk-neutral density (RND). Using a controlled synthetic benchmark (with ground truth densities) and a chronological NIFTY benchmark (testing held-out market prices), it systematically compares two-component lognormal mixture, DeepONet, Transformer, and SVI methods. Results show no universal winner: the mixture achieves the lowest aggregate error on synthetic data, while DeepONet excels in 1% quantile and variance reductions. Numerical conditioning reveals that over 75% of pricing directions are numerically null, and two densities separated by L1=0.061 produce identical prices. On NIFTY data, traditional mixture and SVI remain more accurate than deep learning operators. The evidence supports target-dependent inductive bias over a one-size-fits-all approach.

## Key points

- The two-component lognormal mixture has the lowest aggregate error on the synthetic benchmark, while DeepONet reduces 1% quantile and variance errors by 39.0% and 34.6% respectively.
- Numerical conditioning shows 95 of 126 pricing directions are numerically null, and two densities with L1=0.061 produce identical option prices.
- On real NIFTY data, traditional mixture and SVI fits remain far more accurate than deep learning operators.
- The study advocates for target-dependent inductive bias, cautioning against deep learning as a universal solution for financial pricing.

## Full text

Accurate option prices do not imply accurate recovery of the latent risk-neutral density. We study this distinction with two complementary benchmarks. A controlled benchmark exposes simulator-truth densities for latent evaluation, while a chronological NIFTY benchmark tests only held-out market prices. A two-component lognormal mixture has the lowest aggregate price, $L^1$, Wasserstein, and fixed-tail errors on the synthetic benchmark. Learned operators retain narrower strengths: DeepONet reduces 1% quantile and variance error by 39.0% and 34.6% relative to the mixture, and a quote transformer reduces $L^1$ by 16.4% on the structurally misspecified Merton family. A numerical conditioning analysis explains why these rankings can differ: after enforcing mass and forward constraints, 95 of 126 pricing directions are numerically null, and two densities separated by $L^1 = 0.061$ produce identical prices on the covered strikes. On 524 held-out NIFTY calls, validation-selected test-time adaptation reduces DeepONet RMSE by 28.3%, but per-expiry mixture and SVI fits remain much more accurate. The evidence supports target-dependent inductive bias, not a universal winner.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_c3815c2f60fd93bb5c516934