Paper: arXiv 2508.02759
Authors: Eduardo Abi Jaber, Louis-Amand Gérard
Abstract
We investigate the use of path signatures in a machine learning context for hedging exotic derivatives under non-Markovian stochastic volatility models. In a deep learning setting, we use signatures as features in feedforward neural networks and show that they outperform LSTMs in most cases, with orders of magnitude less training compute. In a shallow learning setting, we compare two regression approaches: the first directly learns the hedging strategy from the expected signature of the price process; the second models the dynamics of volatility using a signature volatility model, calibrated on the expected signature of the volatility. Solving the hedging problem in the calibrated signature volatility model yields more accurate and stable results across different payoffs and volatility dynamics.
Complexity vs Empirical Score
- Math Complexity: 7.5/10
- Empirical Rigor: 4.0/10
- Quadrant: Lab Rats — high math complexity, limited empirical testing
Why this score: The paper is mathematically dense, involving advanced concepts from tensor algebra and stochastic calculus to define path signatures, and includes theoretical proofs like universal approximation theorems. However, it primarily presents a methodology and comparative analysis without providing code, detailed backtesting metrics, or specific dataset results, focusing more on theoretical and algorithmic contributions.
Research Flowchart
flowchart TD A["Research Goal:<br>Hedging exotic derivatives<br>under non-Markovian<br>stochastic volatility"] --> B["Input Data:<br>Simulated price paths<br>with complex volatility dynamics"] B --> C["Deep Learning:<br>Signatures as features<br>in Feedforward Neural Networks"] B --> D["Shallow Learning:<br>Signature Volatility Model<br>+ Regression Strategies"] C --> E["Compare with<br>LSTM baseline"] D --> F["Calibration:<br>Match expected signatures<br>of volatility process"] C & E & F --> G["Key Findings:<br>Signatures outperform LSTMs<br>with less compute.<br>Signature models yield<br>more stable hedging strategies."]
Evidence Card
What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card
Proposes
The paper proposes using path signatures as features in feed‑forward neural networks for hedging exotic derivatives, showing they outperform LSTMs with far less training compute.
Source sentence
In a deep learning setting, we use signatures as features in feedforward neural networks and show that they outperform LSTMs in most cases, with orders of magnitude less training compute.
Assumes 6
- The spot price follows a geometric Brownian motion for the polynomial payoff experiment. model
Source sentence
where S is a geometric Brownian motion in order to have an explicit solution to compare the methods to.
- The European call payoff assumes the underlying follows the Heston model with CIR variance dynamics. model
Source sentence
where S follows the Heston model with its variance Vt = Σ2 t having CIR dynamics (5.2).
- The Asian call payoff assumes a geometric price process with delayed‑equation volatility. model
Source sentence
where S will be geometric with delayed-equation (DE) volatility (5.3).
- The methods assume access to the expected signature of the price or volatility, either exactly or via Monte‑Carlo simulation. data
Source sentence
We assume throughout this section that we are given such data (either exactly or through Monte Carlo simulations).
Show 2 more
- Linear signature regressions are agnostic to the underlying dynamics and can be applied in general contexts. other
Source sentence
By contrast, the linear signature regressions are agnostic to the underlying dynamics and can be applied in more general contexts.
- Training and evaluation are performed over multiple random initialisations (50 for SNN, 10 for RNN). execution
Source sentence
All numerical experiments have been averaged over 50 iterations for the SNN and 10 for the RNN, lower for obvious time reasons.
Data
Synthetic data only.
Costs
Not modeled
Finds 5
- Signature‑based feed‑forward networks achieve better hedging performance than LSTMs while requiring orders of magnitude less training compute. performance
Source sentence
In a deep learning setting, we use signatures as features in feedforward neural networks and show that they outperform LSTMs in most cases, with orders of magnitude less training compute.
- Calibrating a signature volatility model and solving the hedging problem within it yields more accurate and stable results across payoffs and volatility dynamics. performance
Source sentence
Solving the hedging problem in the calibrated signature volatility model yields more accurate and stable results across different payoffs and volatility dynamics.
- Both signature and log‑signature neural networks plateau after truncation order 2, with the signature NN achieving lower mean‑squared P&L than the log‑signature NN under the Heston model. performance
Source sentence
Figure 12 shows that the signature and log‑signature have a significantly different impact on training with the Log‑Signature NN plateauing relatively high and early in the truncation, whereas the Signature NN goes lower and does not seems to plateau under the Heston model.
- Most of the hedging performance can be attributed to the first two or three orders of the signature. theoretical
Source sentence
conclusions are much less clear but we can still see that most of the performance can be attributed to the first 2 or 3 orders of the signature.
- Higher truncation orders beyond 3 provide little to no additional benefit and may even delay convergence. negative
Source sentence
However, apart from a small improvement between truncation 2 and 3 for the look‑back call option, it seems that higher orders either don’t help or actually delay the convergence.
Checked by others
Contradicted by
- Option pricing under non-Markovian stochastic volatility models: A deep signature approach
Compare the findings
This paper: Higher truncation orders beyond 3 provide little to no additional benefit and may even delay convergence.
That paper: Approximation errors for option prices decrease monotonically with higher truncation levels for both SDE and PDE schemes.
- Sig-Splines: universal approximation and convex calibration of time series generative models
Compare the findings
This paper: Higher truncation orders beyond 3 provide little to no additional benefit and may even delay convergence.
That paper: Higher orders of truncation improve autocorrelation metrics, indicating better capture of serial independence and volatility clustering.
2 papers in the archive : Deep kernel hedging
Code
No repository by the authors found in the paper.
Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.
Cited References (58)
- A primer on the signature method in machine learning (2016) — link
- Deep signature transforms (2019)
- Optimal stopping with signatures (2023)
- Joint calibration to SPX and VIX options with signature-based models — → 2301.13235
- Non-parametric Pricing and Hedging of Exotic Derivatives (2020) — link
- Lie Elements and an Algebra Associated With Shuffles (1958)
- The algebra of iterated stochastic integrals (1994) — link
- Perfect hedging in rough Heston models (2017) — link
and 50 more
- A Guided Tour Through Quadratic Hedging Approaches (2001) — link
- Signature Volatility Models: Pricing and Hedging with Fourier (2025) — link
- Deep Hedging (2018) — link
- SigFormer: Signature Transformers for Deep Hedging (2023) — link
- Discretely sampled signals and the rough Hoff process (2016) — link
- Pricing American options under rough volatility using deep-signatures and signature-kernels — → 2501.06758
- Learning stochastic differential equations using RNN with log signature features (2019) — link
- Calculation of Iterated-Integral Signatures and Log Signatures (2017) — link
- Long Short-Term Memory (1997) — link
- Attention is All you Need (2017) — link
- Adam: A Method for Stochastic Optimization (2017) — link
- A Theory of the Term Structure of Interest Rates (1985)
- A Closed-Form Solution for Options with Stochastic Volatility with Applications to Bond and Currency Options (1993) — link
- A new look at the Heston characteristic function (2009) — link
- Simulating integrated Volterra square-root processes and Volterra Heston models via Inverse Gaussian — → 2504.19885
- Path-dependent processes from signatures (2024) — link
- Hedging of Non-redundant Contingent Claims (1985) — link
- B rownian Motion and Stochastic Calculus (1988)
- Pricing under rough volatility (2016) — link
- Integration of Paths, Geometric Invariants and a Generalized Baker- Hausdorff Formula (1957)
- Volatility models in practice: Rough, Path-dependent or Markovian? — → 2401.03345
- Modeling and analysis of stochastic differential equations driven by point processes (1978) — link
- Modeling and approximation of stochastic differential equations driven by semimartingales † (1981) — link
- Signature-Based Models: Theory and Calibration (2023) — link
- Pricing American options under rough volatility using deep-signatures and signature-kernels — → 2501.06758
- Differential Equations Driven by Rough Paths: 'E cole d’ 'E t 'e de Probabilit 'e s de Saint-Flour XXXIV - 2004 (2007) — link
- S ignatory: differentiable computations of the signature and logsignature transforms, on both CPU and GPU (2021)
- Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016) — link
- Dota 2 with Large Scale Deep Reinforcement Learning (2019) — link
- Grandmaster level in StarCraft II using multi-agent reinforcement learning (2019) — link
- Stochastic Control with Signatures (2024) — link
- Learning from the past, predicting the statistics for the future, learning an evolving system (2016) — link
- Universal approximation theorems for continuous functions of c`adl`ag paths and L'evy-type signature models (2023) — link
- Parameter estimation and bias correction for diffusion processes (2009) — link
- Decoupled Weight Decay Regularization (2019) — link
- Martingale property and moment explosions in signature volatility models — → 2503.17103
- Problems in stochastic analysis. Connections between rough paths and non-commutative harmonic analysis (2003)
- Extracting information from the signature of a financial data stream (2014) — link
- Application of the Signature Method to Pattern Recognition in the CEQUEL Clinical Trial (2016) — link
- A signature-based machine learning model for distinguishing bipolar disorder and borderline personality disorder (2018) — link
- Learning Spatial-Semantic Context with Fully Convolutional Recurrent Network for Online Handwritten Chinese Text Recognition (2017) — link
- Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition (2019) — link
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (2014) — link
- Kernel Density Estimators (1992) — link
- Efficiently Modeling Long Sequences with Structured State Spaces (2022) — link
- Sig-SDEs model for quantitative finance (2020)
- Neural networks for option pricing and hedging: a literature review (2020) — link
- Deep Hedging under Rough Volatility (2021) — link
- Signature Trading: A Path-Dependent Extension of the Mean-Variance Framework with Exogenous Signals — → 2308.15135
- Signature SDEs from an affine and polynomial perspective — → 2302.01362
8 of 58 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.