q-fin.PRMar 27, 2026

STN-GPR: A Singularity Tensor Network Framework for Efficient Option Pricing

Authors: Dominic Gribben, Carolina Allende, Alba Villarino, Aser Cortines, Mazen Ali, Román Orús, Pascal Oswald, Noureddine Lehdili

Organizations: Multiverse Computing, Paseo de Miramón 170, 20014 San Sebastián, Spain · Multiverse Computing, rue de la Croix Martre, 91120 Palaiseau, France · DIPC, Paseo Manuel de Lardizabal 4, E-20018 San Sebastián, Spain · Ikerbasque Foundation for Science, Maria Diaz de Haro 3, E-48013 Bilbao, Spain · 

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We develop a tensor-network surrogate for option pricing, targeting large-scale portfolio revaluation problems arising in market risk management (e.g., VaR and Expected Shortfall computations). The method involves representing high-dimensional price surfaces in tensor-train (TT) form using TT-cross approximation, constructing the surrogate directly from black-box price evaluations without materializing the full training tensor. For inference, we use a Laplacian kernel and derive TT representations of the kernel matrix and its closed-form inverse in the noise-free setting, enabling TT-based Gaussian process regression without dense matrix factorization or iterative linear solves. We found that hyperparameter optimization consistently favors a large kernel length-scale and show that in this regime the GPR predictor reduces to multilinear interpolation for off-grid inputs; we also derive a low-rank TT representation for this limit. We evaluate the approach on five-asset basket options over an eight dimensional parameter space (asset spot levels, strike, interest rate, and time to maturity). For European geometric basket puts, the tensor surrogate achieves lower test error at shorter training times than standard GPR by scaling to substantially larger effective training sets. For American arithmetic basket puts trained on LSMC data, the surrogate exhibits more favorable scaling with training-set size while providing millisecond-level evaluation per query, with overall runtime dominated by data generation.

Figures & tables

Figure 1: Error in pricing a European put geometric basket option. Comparison in test error of TT-interp and GPR approaches as a function of the training time for varying training set sizes.
Figure 2: Error in pricing a American put arithmetic basket option. Comparison in test error of TT-interp and GPR approaches as a function of the training time for varying training set sizes. Here the training time includes both the time taken to generate the dataset and, for GPR , the time taken to tune hyperparameters.
More in this topic

Surrogate Modeling

Surrogate modeling builds faster or more interpretable approximations of expensive simulations and black-box models.

See all 226 papers

Explore similar work

CardsList
Apr 29, 2026

Laplace Approximation for Bayesian Tensor Network Kernel Machines

Uncertainty estimation is essential for robust decision-making in the presence of ambiguous or out-of-distribution inputs. Gaussian Processes (GPs) are classical kernel-based models that offer principled uncertainty quantification and perform well on small- to medium-scale datasets. Alternatively, formulating the weight space learning problem under tensor network assumptions yields scalable tensor network kernel machines. However, these assumptions break Gaussianity, complicating standard probabilistic inference. This raises a fundamental question: how can tensor network kernel machines provide principled uncertainty estimates? We propose a novel Bayesian Tensor Network Kernel Machine (LA-TNKM) that employs a (linearized) Laplace approximation for Bayesian inference. A comprehensive set of numerical experiments shows that the proposed method consistently matches or surpasses Gaussian Processes and Bayesian Neural Networks (BNNs) across diverse UCI regression benchmarks, highlighting both its effectiveness and practical relevance.

Albert Saiapin, Kim Batselier

1Delft Center for Systems and Control, Delft University of Technology

Uncertainty QuantificationBayesian InferenceKernel Methods
AskPDF
Jun 1, 2026

Scalable Derivative Gaussian Processes via Exact Gradient Reduction

Gradient observations can substantially improve Gaussian process (GP) surrogates, particularly in high-dimensional settings where function evaluations are expensive. However, exact inference with nn function values and nn full gradients in dd dimensions scales cubically in the joint state size, imposing an intractable O(n3d3)\mathcal{O}(n^3 d^3) computational bottleneck. We introduce TERA, a highly scalable derivative GP method based on target-specific exact gradient reduction. We prove that for stationary kernels, the gradient components orthogonal to the directions connecting the target and conditioning points are conditionally independent of the target function value; consequently, the exact conditional density is fully characterized by at most m2m^2 directional derivatives once a conditioning set of size mm is specified. By using these reduced, dimension-free conditionals as local factors in a Vecchia approximation, TERA effectively decouples nn and dd from the dense matrix inversion. This reduces the per-target evaluation cost to O(dm2+m6)\mathcal{O}(dm^2 + m^6) time and O(dm2+m4)\mathcal{O}(dm^2 + m^4) memory, leaving the underlying derivative GP model mathematically unchanged. Empirical evaluations demonstrate that TERA achieves state-of-the-art predictive accuracy while operating orders of magnitude faster than standard derivative GPs. Crucially, both computation time and peak GPU memory remain essentially flat with respect to dd, enabling highly scalable inference in high-dimensional spaces.

Hyunseok Seung, Matthias Katzfuss

Department of Statistics · University of Wisconsin–Madison · Madison, WI, 53706

Surrogate ModelingGaussian ProcessesGaussian Process Regression
AskPDF
Aug 3, 2026

Neural Networks with Local Converging Inputs for Efficient Options Pricing Models

We present a novel application of Neural Networks with Local Converging Inputs (NNLCI) to improve the efficiency of existing numerical methods for pricing multi-asset options. The most concise input format for NNLCI has been introduced, offering substantial convenience and efficiency. NNLCI uses a neural network to locally correct solutions from a coarse mesh and a refined mesh (relative to the coarse one), requiring only a minimal amount of high-fidelity training data. We demonstrate this approach on cash-or-nothing options under the Black-Scholes equation in one, two, and three spatial dimensions, and on single-asset down-and-out barrier call options under the Heston stochastic-volatility model (whose pricing PDE is two-dimensional in the spot price SS and the instantaneous variance vv). In each case, NNLCI reduces the root-mean-square error (RMSE) of the refined-mesh numerical solution by a factor of approximately 4-12 on test sets, even when the neural network is trained on only a small subset of parameter combinations. These results demonstrate that NNLCI significantly reduces computational requirements for high-dimensional problems in real-time options trading and risk management, offering low training costs and strong generalization ability.

Harris Cobb, Wenbo Hao, Yingjie Liu

School of Mathematics, Georgia Institute of Technology, Atlanta, GA 30332

Neural Surrogate ModelingNeural PDE SolversQuantitative Finance
AskPDF