Approximating Young Measures With Deep Neural Networks

Rayehe Karimi Mahabadi, Jianfeng Lu, Hossein Salahshoor

TL;DR

This paper introduces a deep learning framework to solve non-convex variational problems by approximating Young measures—mathematical objects that describe the "average" behavior of rapidly oscillating sequences. By representing these measures as the push-forward of Gaussian distributions through a neural network, the authors transform difficult, oscillatory optimization problems into a stable, convex-like training process.

What Problem Does This Paper Address?

In physics and materials science, we often try to find the "lowest energy state" of a system. Mathematically, this is a variational problem. However, many real-world systems (like shape-memory alloys or micromagnetics) have non-convex energy landscapes.

When you try to minimize energy in these systems, the solution doesn't settle into a single smooth state. Instead, it creates "microstructures"—infinitely fine oscillations between different stable phases. Standard numerical methods (like Finite Elements) fail here; as you refine the mesh, the solution just oscillates faster and never converges.

Young measures are the theoretical "fix." Instead of looking for a single function value at a point, a Young measure gives you a probability distribution of values. While powerful, Young measures are notoriously difficult to compute because they are high-dimensional and live in the abstract space of measures rather than simple functions.

Methods

The authors propose a novel neural network architecture to represent and find these elusive measures:

  1. The Push-Forward Ansatz: Instead of trying to learn a probability density directly (which is hard), they learn a transport map $f$. This map takes a simple, standard Gaussian variable $\xi$ and transforms ("pushes forward") it into the desired Young measure.
  2. Neural Network Architecture: They use a Residual Network (ResNet) to parameterize a potential function $F$. The transport map is then defined as the gradient of this potential ($\nabla_\xi F$), which helps ensure the resulting measure has nice mathematical properties.
  3. Physics-Informed Loss Function: The "training" isn't done on labeled data. Instead, the loss function is the relaxed energy functional itself. They also add penalty terms to enforce boundary conditions and a "curl-free" condition (ensuring the learned distributions represent a valid gradient field in 2D).
  4. Automatic Differentiation: They leverage the power of modern deep learning frameworks to compute the complex derivatives required by the variational problem directly within the loss function.

Datasets

Since this is a fundamental math/physics paper, the "datasets" are actually canonical numerical benchmarks used to test variational solvers:

  • 1D Bolza Problem: A classic "toy" problem where the energy is minimized by a sequence of "zig-zags" with slopes of $+1$ and $-1$.
  • Quasi-1D Problem: A 2D square domain where the energy depends only on one partial derivative, testing the transition from 1D to 2D.
  • 2D Symmetric Four-Well Problem: A complex landscape with four equivalent energy minima, forcing the system to choose a distribution across multiple "wells."
  • 2D Non-Symmetric Two-Well Problem: A case where the exact solution is not known a priori, demonstrating the model's utility for discovery.

Key Insights and Ideas

  • Convexification via Measures: The paper leans on the fact that while the original problem is non-convex in function space, it becomes convex in the space of Young measures. The neural network acts as the bridge to make this space searchable.
  • Bypassing Analytical Relaxation: Usually, to solve these problems, mathematicians must first perform a "quasiconvexification" of the energy—a step that is analytically impossible for most complex materials. This DNN approach works directly with the original energy, letting the network "discover" the relaxation.
  • Energy-Controlled Error: The authors show that if the energy density is coercive, the distance between the true Young measure and the neural approximation (in the Wasserstein-2 metric) is bounded by the difference in their energies. This provides a theoretical safety net for using energy as a loss function.

Key Results

  • Atomic Concentration: In the 1D Bolza problem, the network correctly learned a distribution concentrated exactly at $+1$ and $-1$ with 50/50 probability, matching the theoretical limit.
  • Microstructure Capture: In 2D cases, the model successfully captured the "bimodal" distribution of gradients required to satisfy conflicting boundary conditions and energy minima.
  • Zero-Effective Solutions: For the four-well problem, the network predicted an "effective" solution (the average/barycenter) of nearly zero everywhere, while correctly identifying that the underlying material is actually oscillating between high-gradient states.
  • Generalization: The framework proved robust enough to handle Case 4, where no closed-form solution exists, providing a qualitative look at how non-symmetric microstructures form.

Limitations and Future Work

  • Dimensionality Challenges: While the method handles 2D physical space well, the "latent" space (the Gaussian variables) adds dimensions. The authors noted numerical difficulties in computing the four-dimensional map $F$ for 2D problems.
  • Homogeneity: The learned measures weren't perfectly homogeneous across the domain, likely due to the difficulty of balancing the "curl-free" penalty with the energy minimization.
  • Scaling to Vector Fields: The current work focuses on scalar fields ($u: \Omega \to \mathbb{R}$). The authors suggest the next logical step is extending this to vector-valued fields, which would allow for the simulation of real-world crystal plasticity and complex alloy microstructures.

Summary updated

Abstract

Parametrized measures (or Young measures) enable to reformulate non-convex variational problems as convex problems at the cost of enlarging the search space from space of functions to space of measures. To benefit from such machinery, we need powerful tools for approximating measures. We develop a deep neural network approximation of Young measures in this paper. The key idea is to write the Young measure as push-forward of Gaussian measures, and reformulate the problem of finding Young measures to finding the corresponding push-forward. We approximate the push-forward map using deep neural networks by encoding the reformulated variational problem in the loss function. After developing the framework, we demonstrate the approach in several numerical examples. We hope this framework and our illustrative computational experiments provide a pathway for approximating Young measures in their wide range of applications from modeling complex microstructure in materials to non-cooperative games.
BibTeX
@misc{mahabadi2025approximating,
  author = {Rayehe Karimi Mahabadi and Jianfeng Lu and Hossein Salahshoor},
  title = {{Approximating Young Measures With Deep Neural Networks}},
  year = {2025},
  eprint = {2511.00233},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2511.00233},
}
Figure