Physics-Informed Quantum Machine Learning for Solving Partial
Differential Equations
- URL: http://arxiv.org/abs/2312.09215v1
- Date: Thu, 14 Dec 2023 18:46:35 GMT
- Title: Physics-Informed Quantum Machine Learning for Solving Partial
Differential Equations
- Authors: Abhishek Setty, Rasul Abdusalamov, Mikhail Itskov
- Abstract summary: We propose a tensor product over a summation of Pauli-Z operators as a change in the measurement observables.
This idea has been tested on solving the complex dynamics of a Riccati equation.
A new quantum circuit structure is proposed to approximate multivariable functions, tested on solving a 2D Poisson's equation.
- Score: 0.0
- License: http://creativecommons.org/licenses/by-nc-nd/4.0/
- Abstract: In this work, we solve differential equations using quantum Chebyshev feature
maps. We propose a tensor product over a summation of Pauli-Z operators as a
change in the measurement observables resulting in improved accuracy and
reduced computation time for initial value problems processed by floating
boundary handling. This idea has been tested on solving the complex dynamics of
a Riccati equation as well as on a system of differential equations.
Furthermore, a second-order differential equation is investigated in which we
propose adding entangling layers to improve accuracy without increasing the
variational parameters. Additionally, a modified self-adaptivity approach of
physics-informed neural networks is incorporated to balance the multi-objective
loss function. Finally, a new quantum circuit structure is proposed to
approximate multivariable functions, tested on solving a 2D Poisson's equation.
Related papers
- ConDiff: A Challenging Dataset for Neural Solvers of Partial Differential Equations [42.69799418639716]
We present ConDiff, a novel dataset for scientific machine learning.
ConDiff focuses on the diffusion equation with varying coefficients, a fundamental problem in many applications of parametric partial differential equations (PDEs)
This class of problems is not only of great academic interest, but is also the basis for describing various environmental and industrial problems.
In this way, ConDiff shortens the gap with real-world problems while remaining fully synthetic and easy to use.
arXiv Detail & Related papers (2024-06-07T07:35:14Z) - Solving Systems of Linear Equations: HHL from a Tensor Networks Perspective [39.58317527488534]
We present an algorithm for solving systems of linear equations based on the HHL algorithm with a novel qudits methodology.
We perform a quantum-inspired version on tensor networks, taking advantage of their ability to perform non-unitary operations such as projection.
arXiv Detail & Related papers (2023-09-11T08:18:41Z) - Physics-informed Neural Network: The Effect of Reparameterization in
Solving Differential Equations [0.0]
Complicated physics mostly involves difficult differential equations, which are hard to solve analytically.
In recent years, physics-informed neural networks have been shown to perform very well in solving systems with various differential equations.
arXiv Detail & Related papers (2023-01-28T07:53:26Z) - Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural
Networks on Coupled Ordinary Differential Equations [64.78260098263489]
In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs)
We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases.
We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
arXiv Detail & Related papers (2022-10-14T15:01:32Z) - Integral Transforms in a Physics-Informed (Quantum) Neural Network
setting: Applications & Use-Cases [1.7403133838762446]
In many computational problems in engineering and science, function or model differentiation is essential, but also integration is needed.
In this work, we propose to augment the paradigm of Physics-Informed Neural Networks with automatic integration.
arXiv Detail & Related papers (2022-06-28T17:51:32Z) - Physics Informed RNN-DCT Networks for Time-Dependent Partial
Differential Equations [62.81701992551728]
We present a physics-informed framework for solving time-dependent partial differential equations.
Our model utilizes discrete cosine transforms to encode spatial and recurrent neural networks.
We show experimental results on the Taylor-Green vortex solution to the Navier-Stokes equations.
arXiv Detail & Related papers (2022-02-24T20:46:52Z) - Message Passing Neural PDE Solvers [60.77761603258397]
We build a neural message passing solver, replacing allally designed components in the graph with backprop-optimized neural function approximators.
We show that neural message passing solvers representationally contain some classical methods, such as finite differences, finite volumes, and WENO schemes.
We validate our method on various fluid-like flow problems, demonstrating fast, stable, and accurate performance across different domain topologies, equation parameters, discretizations, etc., in 1D and 2D.
arXiv Detail & Related papers (2022-02-07T17:47:46Z) - Quantum Model-Discovery [19.90246111091863]
Quantum algorithms for solving differential equations have shown a provable advantage in the fault-tolerant quantum computing regime.
We extend the applicability of near-term quantum computers to more general scientific machine learning tasks.
Our results show a promising path to Quantum Model Discovery (QMoD) on the interface between classical and quantum machine learning approaches.
arXiv Detail & Related papers (2021-11-11T18:45:52Z) - QBoost for regression problems: solving partial differential equations [0.0]
The hybrid algorithm is capable of finding a solution to a partial differential equation with good precision and favorable scaling in the required number of qubits.
The classical part is composed by training several regressors, capable of solving a partial differential equation using machine learning.
The quantum part consists of adapting the QBoost algorithm to solve regression problems.
arXiv Detail & Related papers (2021-08-30T16:13:04Z) - Solving nonlinear differential equations with differentiable quantum
circuits [21.24186888129542]
We propose a quantum algorithm to solve systems of nonlinear differential equations.
We use automatic differentiation to represent function derivatives in an analytical form as differentiable quantum circuits.
We show how this approach can implement a spectral method for solving differential equations in a high-dimensional feature space.
arXiv Detail & Related papers (2020-11-20T13:21:11Z) - Scalable Gradients for Stochastic Differential Equations [40.70998833051251]
adjoint sensitivity method scalably computes gradients of ordinary differential equations.
We generalize this method to differential equations, allowing time-efficient and constant-memory computation.
We use our method to fit neural dynamics defined by networks, achieving competitive performance on a 50-dimensional motion capture dataset.
arXiv Detail & Related papers (2020-01-05T23:05:55Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.