Mean-field neural networks: learning mappings on Wasserstein space
- URL: http://arxiv.org/abs/2210.15179v3
- Date: Mon, 18 Sep 2023 07:34:11 GMT
- Title: Mean-field neural networks: learning mappings on Wasserstein space
- Authors: Huy\^en Pham and Xavier Warin
- Abstract summary: We study the machine learning task for models with operators mapping between the Wasserstein space of probability measures and a space of functions.
Two classes of neural networks are proposed to learn so-called mean-field functions.
We present different algorithms relying on mean-field neural networks for solving time-dependent mean-field problems.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We study the machine learning task for models with operators mapping between
the Wasserstein space of probability measures and a space of functions, like
e.g. in mean-field games/control problems. Two classes of neural networks,
based on bin density and on cylindrical approximation, are proposed to learn
these so-called mean-field functions, and are theoretically supported by
universal approximation theorems. We perform several numerical experiments for
training these two mean-field neural networks, and show their accuracy and
efficiency in the generalization error with various test distributions.
Finally, we present different algorithms relying on mean-field neural networks
for solving time-dependent mean-field problems, and illustrate our results with
numerical tests for the example of a semi-linear partial differential equation
in the Wasserstein space of probability measures.
Related papers
- Chebyshev Spectral Neural Networks for Solving Partial Differential Equations [0.0]
The study uses a feedforward neural network model and error backpropagation principles, utilizing automatic differentiation (AD) to compute the loss function.
The numerical efficiency and accuracy of the CSNN model are investigated through testing on elliptic partial differential equations, and it is compared with the well-known Physics-Informed Neural Network(PINN) method.
arXiv Detail & Related papers (2024-06-06T05:31:45Z) - Solving partial differential equations with sampled neural networks [1.8590821261905535]
Approximation of solutions to partial differential equations (PDE) is an important problem in computational science and engineering.
We discuss how sampling the hidden weights and biases of the ansatz network from data-agnostic and data-dependent probability distributions allows us to progress on both challenges.
arXiv Detail & Related papers (2024-05-31T14:24:39Z) - An Analytic Solution to Covariance Propagation in Neural Networks [10.013553984400488]
This paper presents a sample-free moment propagation technique to accurately characterize the input-output distributions of neural networks.
A key enabler of our technique is an analytic solution for the covariance of random variables passed through nonlinear activation functions.
The wide applicability and merits of the proposed technique are shown in experiments analyzing the input-output distributions of trained neural networks and training Bayesian neural networks.
arXiv Detail & Related papers (2024-03-24T14:08:24Z) - Quantile and moment neural networks for learning functionals of
distributions [0.0]
We study news neural networks to approximate function of distributions in a probability space.
Two classes of neural networks based on quantile and moment approximation are proposed to learn these functions.
arXiv Detail & Related papers (2023-03-20T12:23:31Z) - Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation [59.45669299295436]
We propose a Monte Carlo PDE solver for training unsupervised neural solvers.
We use the PDEs' probabilistic representation, which regards macroscopic phenomena as ensembles of random particles.
Our experiments on convection-diffusion, Allen-Cahn, and Navier-Stokes equations demonstrate significant improvements in accuracy and efficiency.
arXiv Detail & Related papers (2023-02-10T08:05:19Z) - Discretization Invariant Networks for Learning Maps between Neural
Fields [3.09125960098955]
We present a new framework for understanding and designing discretization invariant neural networks (DI-Nets)
Our analysis establishes upper bounds on the deviation in model outputs under different finite discretizations.
We prove by construction that DI-Nets universally approximate a large class of maps between integrable function spaces.
arXiv Detail & Related papers (2022-06-02T17:44:03Z) - Learning Neural Network Subspaces [74.44457651546728]
Recent observations have advanced our understanding of the neural network optimization landscape.
With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
With a similar computational cost as training one model, we learn lines, curves, and simplexes of high-accuracy neural networks.
arXiv Detail & Related papers (2021-02-20T23:26:58Z) - Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs.
Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing.
We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs)
We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
arXiv Detail & Related papers (2020-09-08T13:26:51Z) - Provably Efficient Neural Estimation of Structural Equation Model: An
Adversarial Approach [144.21892195917758]
We study estimation in a class of generalized Structural equation models (SEMs)
We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent.
For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
arXiv Detail & Related papers (2020-07-02T17:55:47Z) - Multipole Graph Neural Operator for Parametric Partial Differential
Equations [57.90284928158383]
One of the main challenges in using deep learning-based methods for simulating physical systems is formulating physics-based data.
We propose a novel multi-level graph neural network framework that captures interaction at all ranges with only linear complexity.
Experiments confirm our multi-graph network learns discretization-invariant solution operators to PDEs and can be evaluated in linear time.
arXiv Detail & Related papers (2020-06-16T21:56:22Z) - Neural Operator: Graph Kernel Network for Partial Differential Equations [57.90284928158383]
This work is to generalize neural networks so that they can learn mappings between infinite-dimensional spaces (operators)
We formulate approximation of the infinite-dimensional mapping by composing nonlinear activation functions and a class of integral operators.
Experiments confirm that the proposed graph kernel network does have the desired properties and show competitive performance compared to the state of the art solvers.
arXiv Detail & Related papers (2020-03-07T01:56:20Z)
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.