Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

121242363484 · Jun 202019922001200920172026
48 results for PDE estimates

Adapts PDE method to prove LL^\infty estimates for complex Hessian equations.

problem Proving LL^\infty estimates for complex Hessian equations on transverse Kähler manifolds.
method Adapts PDE approach of Guo-Phong-Tong and Guo-Phong-Tong-Wang [17, 18].
result Obtains LL^\infty estimate for transverse complex Monge-Ampère equations.

DeepONets combine neural networks with physics constraints for PDEs and parameter estimation.

problem Estimating parameters in PDEs with uncertainty quantification.
method Physics-informed neural networks (PINNs) integrated with Deep Operator Networks (DeepONets) for Bayesian inference.
result Robust and accurate solutions with comprehensive uncertainty quantification.

The paper explores how multiway data from PDEs can be accurately tracked using EnKF with specific covariance and precision estimators.

problem Tracking sparse and multiway structures in dynamical processes governed by PDEs.
method Examined several multiway covariance and precision matrix estimators in the context of physics-driven forecasting and EnKF.
result Multiway data from Poisson and convection-diffusion PDEs can be accurately tracked using EnKF with appropriate estimators.

Paper establishes LL^{\infty} estimates for complex Monge-Ampere and Hessian equations.

problem Estimating solutions to complex Monge-Ampere and Hessian equations.
method Uses PDE techniques similar to Phong et al to prove LL^{\infty} and Hölder estimates.
result Establishes LL^{\infty} estimates for both complex Monge-Ampere and Hessian equations.

New method detects changepoints in PDEs using optimized neural networks.

problem Detecting changepoints in PDEs with unknown locations and times.
method Online optimized Physics-Informed Neural Networks (PINNs) with Total-Variation penalty.
result Improved parameter estimation and model fitting with changepoints.

Develops a numerical scheme for solving path-dependent FBSDEs and PDEs.

problem Solving path-dependent FBSDEs and PDEs numerically.
method Picard iteration method for FBSDEs, concentration inequality for estimator, supervised learning with neural networks for PDEs.
result Proves convergence and rate of convergence for the Picard iteration method.

Estimating boundaries from point clouds with improved accuracy and rigorous error estimates.

problem Identifying the boundary of a domain from point cloud samples.
method Developed new estimators for normal vectors, distances, and boundary tests; provided error estimates.
result Efficient and accurate estimators for boundary properties on point clouds.

Study generalizes Picard iteration for nonlinear PDEs, deriving bounds on error.

problem Generalize Picard iteration for nonlinear parabolic PDEs.
method Formulate Picard iteration as abstract state-transition model, derive generalization error bounds.
result Picard depth reduction reduces Picard truncation error without increasing estimation error.

Sharp LL^\infty estimates proved for complex Monge-Ampère equations.

problem Proving sharp LL^\infty estimates for complex Monge-Ampère equations.
method PDE proof covering fixed and degenerating background metrics, extends to general fully non-linear equations.
result Sharp LL^\infty estimates proved for complex Monge-Ampère equations.

Unified estimate for complex Monge-Ampère equations on Kähler manifolds.

problem Estimating solutions to complex Monge-Ampère equations on Kähler manifolds.
method Unified approach using PDE methods and entropy bounds to construct comparison metrics.
result Improves previous results on modulus of continuity, stability, and W1,1W^{1,1}-estimates of Green's functions.

New machine learning methods solve complex PDEs with improved accuracy.

problem Solving fully nonlinear PDEs with convex Hamiltonian.
method Rewriting PDE in dual stochastic control form, estimating optimal feedback control with neural network, approximating value function with neural networks.
result Improved estimation of PDE solution and its derivatives, especially the second derivative.

Generative model improved using Liouville PDE-based sliced-Wasserstein flow.

problem Improving generative models for fair regression.
method Transformed sliced-Wasserstein flow into Liouville PDE-based formalism, handling density estimation with normalizing flows of neural ODE.
result Outperforms in convergence and fairness with reduced variance.

Physics-informed GANs estimate elastic moduli from mechanical tests.

problem Estimating spatially-varying elastic moduli from measured deformations.
method Physics-informed Generative Adversarial Networks (PI-GANs) with PDE constraints.
result Generated stiffness samples match true distribution statistics.

Unified framework solves nonlinear PDEs and IPs using Gaussian processes.

problem Solving and identifying parameters in nonlinear PDEs and inverse problems.
method Gaussian process framework approximating solutions as MAP estimators, reducing to finite-dimensional optimization problem.
result Unified method converges in a small number of iterations for various PDEs.

The paper proves well-posedness of nonlocal PDEs related to stochastic control problems.

problem Characterizing equilibrium strategies and value functions for time-inconsistent stochastic control problems.
method Method of continuity and Banach's fixed point arguments, with Schauder prior estimates.
result Global well-posedness of nonlocal fully nonlinear PDEs with sharp a-priori estimates.

New method reduces PDE surrogate model training costs by selectively acquiring time steps.

problem High computational cost of generating training data for PDE surrogate models.
method STAP (Selective Time-Step Acquisition for PDEs) framework that acquires only important time steps.
result Demonstrated effectiveness on several benchmark PDEs, reducing training costs.

Generative network integrates into ROM for PDEs, matching measurements and estimating uncertainties.

problem Predicting and quantifying uncertainties in numerical simulations of PDEs.
method Generative network (GN) integrated into a reduced-order model (ROM) framework for inverse problems.
result GN-based ROM efficiently quantifies uncertainty and matches measurements with high accuracy.

New proof of LL^\infty estimates for Monge-Ampère and Hessian equations on nef classes.

problem Estimating solutions to Monge-Ampère and Hessian equations on nef classes.
method Applying PDE approach to Kähler manifolds to nef classes.
result New proofs of estimates for Monge-Ampère and Hessian equations.

Proposes a method to refine PDE-driven high-dimensional rare-event simulation.

problem Challenges in constructing accurate surrogates for rare-event simulation.
method Adaptive importance sampling framework that refines a locally constructed surrogate.
result Achieves accuracy comparable to true-model adaptive importance sampling with fewer high-fidelity evaluations.

We develop DTs for PDE models using KL-NN and TL, analyzing TL's moment equations and one-shot learning for exactness.

problem Creating accurate digital twins for systems governed by PDEs under changing conditions.
method We use KL-NN surrogate models and transfer learning to construct DTs, analyzing the moment equations and proposing one-shot and few-shot learning methods.
result For linear PDEs, one-shot TL is exact; for nonlinear PDEs, some parameters can be transferred with minimal error.

Sharp LL^\infty estimates for non-Kähler manifolds' PDEs are derived.

problem Sharp LL^\infty estimates for fully nonlinear PDEs on non-Kähler manifolds.
method Comparison with an auxiliary Monge-Ampère equation on a ball with Dirichlet boundary conditions.
result The method yields unique solutions and improves on existing methods.

We propose new machine learning schemes for solving high dimensional nonlinear partial differential equations (PDEs). Relying on the classical backward stochastic differential equation (BSDE) representation of PDEs, our algorithms estimate simultaneously the solution and its gradient by deep neural networks. These appr…

2019-02-05abs ↗pdf ↗

HTE improves PINNs for high-dimensional, high-order PDEs by reducing computational cost and memory usage.

problem Challenges in solving high-dimensional, high-order PDEs with PINNs due to computational cost and memory constraints.
method Introduces Hutchinson Trace Estimation (HTE) to transform Hessian matrix calculations into Hessian vector products (HVP), reducing computational cost and memory usage.
result HTE significantly reduces memory consumption and computational cost, enabling faster and more efficient solution of high-dimensional and high-order PDEs.

We prove a priori estimates for a generalised Monge-Ampère PDE with "non-constant coefficients" thus improving a result of Sun in the Kähler case. We apply this result to the deformed Hermitian Yang-Mills (dHYM) equation of Jacob-Yau to obtain an existence result and a priori estimates for some ranges of the phase angl…

2015-09-03abs ↗pdf ↗

Deep NURBS improves PINNs for solving PDEs on arbitrary geometries.

problem Solving partial differential equations on complex geometries with physics constraints.
method Combines admissible NURBS parametrizations and PINN solver for arbitrary geometries.
result High convergence rate and accuracy for most PDEs using Deep NURBS.

Physics-informed deep learning for PDEs solves forward and inverse problems efficiently.

problem Solving forward and inverse problems in parametric PDEs efficiently and accurately.
method Physics-informed deep latent variable model (PDDLVM) combining deep neural networks, probabilistic modelling, and variational inference.
result Achieves up to three orders of magnitude speed-up compared to traditional FEM while providing coherent uncertainty estimates.