Neural networks solve SPDEs using Wiener chaos expansion.
problem Solving stochastic partial differential equations (SPDEs) numerically.
method Using neural networks in the truncated Wiener chaos expansion.
result Approximation rates for learning SPDE solutions with noise.
Novel framework discovers SPDEs from limited data.
problem Discovering SPDEs from limited data.
method Combines stochastic calculus, variational Bayes, and sparse learning.
result Accurately identifies SPDEs from limited data.
Deep learning approximates SPDE solutions from noise trajectories.
problem Approximating solutions to stochastic partial differential equations (SPDEs).
method Uses neural networks to approximate SPDE solutions based on noise realizations.
result Accurately estimates SPDE solutions and functionals like mean and variance.
SON learns SPDE solutions and uncertainty from noisy data.
problem Uncertainty quantification in SPDEs with unknown model uncertainties.
method Combining DeepONet and SNNs, SON models stochasticity and predicts uncertainty.
result SON accurately captures solution structure and quantifies predictive uncertainty.
Adaptive learning of SPDE solutions using score-based diffusion models.
problem Model errors and reduced accuracy in SPDE solutions due to incomplete physical knowledge and environmental variability.
method Score-based diffusion models with recursive Bayesian inference, incorporating simulation data and observational information.
result Accuracy and robustness of the proposed method demonstrated on benchmark SPDEs.
The paper examines conditions for stochastic invariance of cones in SPDEs with jumps.
problem Stochastic invariance of cones in SPDEs with jumps.
method Sufficient conditions for stochastic invariance of closed convex cones in abstract L2-spaces. result Conditions for stochastic invariance of cones are provided and analyzed.
Conservative SPDEs emerge from fluctuating SGD dynamics in neural networks.
problem Understanding the convergence of stochastic gradient descent to SPDEs.
method Mean-field analysis and central limit theorem for SPDEs.
result Optimal convergence rates for SPDEs derived from SGD.
New graph kernels capture spatio-temporal interactions.
problem Lack of justified spatio-temporal graph kernels for graph problems.
method Derive graph kernels via SPDEs for spatio-temporal modelling.
result Non-separable spatio-temporal graph kernels outperform existing ones.
Bayesian nonparametric models get better posterior estimates via SPDE methods.
problem Estimating posterior distributions in nonparametric Bayesian models.
method Extending diffusion methods to SPDEs on Hilbert spaces for posterior contraction and Laplace approximation.
result Derivation of posterior contraction rates and finite-sample Bernstein von Mises results.
We link SVEs to SPDEs and derive Kolmogorov equations for singular kernels.
problem Solving stochastic Volterra equations with singular kernels.
method Establishing connections between SVEs and SPDEs, using stochastic calculus in Hilbert spaces.
result Solutions of SVEs can be expressed in terms of backward Kolmogorov equations.
Unified framework models multiple financial and insurance term structures.
problem Modeling multiple term structures in various markets.
method Extended Heath-Jarrow-Morton (HJM) approach under real-world probability.
result Characterization of local martingale deflators and existence of affine realizations.
We establish existence, uniqueness and regularity of solution results for a class of backward stochastic partial differential equations with singular terminal condition. The equation describes the value function of non-Markovian stochastic optimal control problem in which the terminal state of the controlled process is…
In this article, we propose a Milstein finite difference scheme for a stochastic partial differential equation (SPDE) describing a large particle system. We show, by means of Fourier analysis, that the discretisation on an unbounded domain is convergent of first order in the timestep and second order in the spatial gri…
New methods solve SPDEs for financial derivative pricing.
problem Deriving the price of financial derivatives using SPDEs.
method Developed a conditional Feynman-Kac formula to solve SPDEs.
result Established new numerical methods for mixed Monte-Carlo PDEs.
New deep learning method approximates Benes filter model.
problem Approximating high-dimensional SPDEs for filtering.
method Deep learning mesh-free neural network representation.
result First study of neural network method for Benes model.
The paper develops methods to price options under rough volatility models using BSPDEs.
problem Pricing options in models with non-Markovian dynamics.
method Backward stochastic partial differential equations (BSPDEs) and deep learning for numerical approximations.
result Existence and uniqueness of weak solutions for general nonlinear BSPDEs.
Paper solves optimal contract problem for fund managers with capital injections and trading constraints.
problem Optimal contract for a fund manager with capital injections and endogenous trading constraints.
method Reduces the problem to an inverse problem of SPDE, proving well-posedness and computing the solution explicitly in the Black-Scholes model.
result Characterizes the solution to the inverse problem through a Stochastic Partial Differential Equation (SPDE).
Proposes a stochastic model for limit order book dynamics.
problem Captures the dynamics of limit order books in financial markets.
method Develops a stochastic partial differential equation (SPDE) model with multiplicative noise.
result Shows efficient estimation and computation methods for the model.
Model for high-frequency trading with rough volatility.
problem High-frequency trading dynamics and rough volatility modeling.
method Stochastic partial differential equation (SPDE) with rough volatility driven by a Hawkes process.
result The volatility path of the SPDE is rougher than that driven by a standard Brownian motion.
We use GANs and signatures to approximate conditional laws in filtering and prediction of diffusion processes.
problem Approximating conditional laws for diffusion processes with noisy observations.
method Conditional GANs combined with signatures for approximation.
result Efficient approximation of conditional laws for diffusion processes.
New method for dynamic valuation in markets with random endowments.
problem Dynamic valuation in markets with random endowments.
method Developed new FBSDE systems and established optimality conditions.
result Established necessary and sufficient conditions for optimality.
We study a constrained optimal control problem with possibly degenerate coefficients arising in models of optimal portfolio liquidation under market impact. The coefficients can be random in which case the value function is described by a degenerate backward stochastic partial differential equation (BSPDE) with singula…
Unified approach solves Kyle model with dynamic information.
problem Solving a generalized Kyle model with dynamic information.
method Monge-Kantorovich duality and backward stochastic partial differential equations.
result Characterization of optimal strategies and pricing rules.
Moving boundary problems allow to model systems with phase transition at an inner boundary. Driven by problems in economics and finance, in particular modeling of limit order books, we consider a stochastic and non-linear extension of the classical Stefan-problem in one space dimension, where the paths of the moving in…
Study on Matérn covariance approximations on grids, finding issues with high-frequency aliasing.
problem Issues with high-frequency aliasing in SPDE approximations of Matérn covariance functions.
method Analysis of aliased spectral densities and numerical simulations.
result SPDE approximations assign too much power at high frequencies and do not improve accuracy as grid spacing decreases.
Backward stochastic partial differential equations of parabolic type in bounded domains are studied in the setting where the coercivity condition is not necessary satisfied and the equation can be degenerate. Some generalized solutions based on the representation theorem are suggested. In addition to problems with a st…
PASTIS method selects simple models from noisy data.
problem Selecting correct models from large candidate libraries.
method PASTIS (Parsimonious Stochastic Inference) using extreme value theory.
result PASTIS outperforms other methods in model identification and predictive capability.
Neural architecture improves geophysical data assimilation with uncertainty quantification.
problem Improving geophysical data interpolation with uncertainty quantification.
method Neural variational data assimilation with SPDE priors.
result Demonstrated improved performance and uncertainty quantification.
Exchange uses incentives to optimize limit order book dynamics.
problem Optimizing market liquidity in fragmented electronic markets.
method Modeling limit order book as SPDE and using control theory to design incentives.
result Exchange can design incentives to modify order book shape and increase liquidity.
Derives new equations for stochastic volatility models.
problem Modeling local-stochastic-volatility models and their derivatives.
method Conditional forward equation, Dupire stochastic PDE, rolling expiry vanilla option SPDE.
result New equations for LSV models and their derivatives.
Maximum principle proves positivity of forward rates in stochastic models.
problem Proving positivity of forward rates in stochastic models.
method Maximum principle for mild solutions to SPDEs with Lipschitz coefficients and Wiener noise.
result Sufficient conditions for positivity of forward rates in the Heath-Jarrow-Morton model.
A novel capsule network model improves surrogate modeling and uncertainty quantification from sparse data.
problem Surrogate modeling and uncertainty quantification of systems from sparse data.
method Adapted Capsule Network (CapsNet) architecture into image-to-image regression encoder-decoder network.
result The proposed approach accurately, efficiently, and robustly predicts responses for arbitrary diffusion fields.
New methods solve complex equations using neural networks.
problem Long-time integration of nonlinear stochastic PDEs.
method Physics-Informed Neural Networks (PINNs) with dynamically orthogonal (DO) and bi-orthogonal (BO) constraints.
result Overcomes limitations of original DO/BO methods and can handle inverse problems.
We formulate stochastic partial differential equations on Riemannian manifolds, moving surfaces, general evolving Riemannian manifolds (with appropriate assumptions) and Riemannian manifolds with random metrics, in the variational setting of the analysis to stochastic partial differential equations. Considering mainly …
The paper develops stochastic models for mortality rates using infinite dimensional processes.
problem Uncertainty in demographic projections of future mortality rates.
method Forward mortality models driven by Wiener process and Poisson random measure.
result Consistency conditions for forward mortality improvements and mortality rates.
Deep neural networks create surrogate models for high-dimensional uncertainty quantification.
problem Uncertainty quantification for systems with many input parameters is computationally infeasible.
method Constructing a cheap-to-evaluate surrogate model using deep neural networks (DNN) to replace a forward model solver.
result DNN surrogate models can learn a map between an arbitrary snapshot of the diffusion field and the response, overcoming traditional SPDE problem constraints.
Clarifies when certain stochastic PDEs have affine solutions.
problem Existence of affine realizations for semilinear SPDEs driven by Lévy processes.
method Analyzes conditions for affine solutions to SPDEs driven by Lévy processes.
result Conditions for the existence of affine realizations are established.
We examine some differential geometric approaches to finding approximate solutions to the continuous time nonlinear filtering problem. Our primary focus is a new projection method for the optimal filter infinite dimensional Stochastic Partial Differential Equation (SPDE), based on the direct L2 metric and on a family o…
Clarifies when certain stochastic PDEs have affine state processes.
problem Characterizing stochastic PDEs with affine state processes.
method Characterization of initial points for affine realizations.
result Characterizes the set of initial points for affine realizations.
Clarifies when solutions to stochastic PDEs stay near given subsets.
problem Understanding the proximity of solutions to stochastic PDEs to given subsets.
method Analyzes distance between closed sets and solutions to stochastic PDEs.
result Clarifies conditions for solutions to stay near given subsets.
The study optimizes Gaussian process approximations for finite-rank models.
problem Posterior behavior of finite-rank approximations differs from parent GP priors.
method Locally supported basis expansions with dependent Gaussian coefficients.
result Finite-rank expansions inherit the same posterior contraction rate as parent GP priors.
Derives new equations for volatility models and option pricing.
problem Modeling and pricing options in local-stochastic-volatility models.
method Develops conditional forward equations and Dupire stochastic PDEs.
result Derives new SPDE for vanilla options.
Paper solves complex control problems using novel SDEs.
problem Solving stochastic differential games for nonlinear systems.
method Uses Deep Forward-Backward SDEs with neural networks.
result Numerical solution validated on two example systems.
A new method uses SPDEs to efficiently model random fields on complex domains.
problem Efficient representation of random fields on complex domains for engineering and machine learning.
method Uses SPDEs to develop a scalable framework for statFEM and GP regression.
result Can model anisotropic, non-stationary random fields with arbitrary smoothness.
Deep learning model solves high-dimensional PDEs using Actor-Critic approach.
problem Solving high-dimensional nonlinear PDEs efficiently.
method Reformulated PDE into BSDE system, inspired by Actor-Critic algorithm for deep RL.
result Improved model with fewer parameters, faster convergence, and less hyperparameter tuning.
Deep neural networks solve high-dimensional PDEs without explicit grids.
problem Solving high-dimensional PDEs using classical methods is computationally infeasible.
method Approximate solution with a deep neural network trained via FBSDEs.
result Deep learning can solve high-dimensional PDEs efficiently.
The paper discusses how to improve machine learning models using partial differential equations.
problem Improving the performance and generalization of machine learning models.
method The paper reframes implicit regularization techniques in deep learning as explicit gradient regularization using partial differential equations.
result Explicit regularization using PDEs can lead to better model performance and generalization.
This paper studies the question of filtering and maximizing terminal wealth from expected utility in a partially information stochastic volatility models. The special features is that the only information available to the investor is the one generated by the asset prices, and the unobservable processes will be modeled …