Compliance Minimization via Physics-Informed Gaussian Processes

• URL: http://arxiv.org/abs/2507.09968v1
• Date: Mon, 14 Jul 2025 06:34:29 GMT
• Title: Compliance Minimization via Physics-Informed Gaussian Processes
• Authors: Xiangyu Sun, Amin Yousefpour, Shirin Hosseinmardi, Ramin Bostanabad,
• Abstract summary: We propose a mesh-free and simultaneous framework based on physics-informed Gaussian processes (GPs)<n>In our approach, we parameterize the design and state variables with GP priors which have independent kernels but share a multi-output neural network (NN) as their mean function.<n>The architecture of this NN is based on Parametric Grid Convolutional Attention Networks (PGCANs) which not only spectral bias issues, but also provide an interpretable mechanism to control design complexity.
• Score: 3.6352820455705372
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Machine learning (ML) techniques have recently gained significant attention for solving compliance minimization (CM) problems. However, these methods typically provide poor feature boundaries, are very expensive, and lack a systematic mechanism to control the design complexity. Herein, we address these limitations by proposing a mesh-free and simultaneous framework based on physics-informed Gaussian processes (GPs). In our approach, we parameterize the design and state variables with GP priors which have independent kernels but share a multi-output neural network (NN) as their mean function. The architecture of this NN is based on Parametric Grid Convolutional Attention Networks (PGCANs) which not only mitigate spectral bias issues, but also provide an interpretable mechanism to control design complexity. We estimate all the parameters of our GP-based representations by simultaneously minimizing the compliance, total potential energy, and residual of volume fraction constraint. Importantly, our loss function exclude all data-based residuals as GPs automatically satisfy them. We also develop computational schemes based on curriculum training and numerical integration to increase the efficiency and robustness of our approach which is shown to (1) produce super-resolution topologies with fast convergence, (2) achieve smaller compliance and less gray area fraction compared to traditional numerical methods, (3) provide control over fine-scale features, and (4) outperform competing ML-based methods.

Related papers

• Efficient Transformed Gaussian Process State-Space Models for Non-Stationary High-Dimensional Dynamical Systems [49.819436680336786]
  We propose an efficient transformed Gaussian process state-space model (ETGPSSM) for scalable and flexible modeling of high-dimensional, non-stationary dynamical systems.<n>Specifically, our ETGPSSM integrates a single shared GP with input-dependent normalizing flows, yielding an expressive implicit process prior that captures complex, non-stationary transition dynamics.<n>Our ETGPSSM outperforms existing GPSSMs and neural network-based SSMs in terms of computational efficiency and accuracy.
  arXiv  Detail & Related papers  (2025-03-24T03:19:45Z)
• Localized Physics-informed Gaussian Processes with Curriculum Training for Topology Optimization [3.6352820455705372]
  We introduce a simultaneous and meshfree topology optimization (TO) framework based on physics-informed Gaussian processes (GPs)<n>Our framework endows all design and state variables via GP priors which have a shared, multi-output mean function that is parametrized via a customized deep neural network (DNN)<n>Our TO approach yields well-defined material interfaces and has a built-in continuation nature that promotes global optimality.
  arXiv  Detail & Related papers  (2025-03-18T22:59:16Z)
• Automatic Joint Structured Pruning and Quantization for Efficient Neural Network Training and Compression [44.35542987414442]
  Structured pruning and quantization are fundamental techniques used to reduce the size of deep neural networks (DNNs)<n>Applying these techniques jointly via co-optimization has the potential to produce smaller, high-quality models.<n>We present the framework GETA, which automatically and efficiently performs joint structured pruning and quantization-aware training on any DNNs.
  arXiv  Detail & Related papers  (2025-02-23T16:28:18Z)
• Simultaneous and Meshfree Topology Optimization with Physics-informed Gaussian Processes [0.0]
  Topology optimization (TO) provides a principled mathematical approach for optimizing the performance of a structure by designing its material spatial distribution in a pre-defined domain and subject to a set of constraints. We develop a new class of TO methods based on the framework of Gaussian processes (GPs) whose mean functions are parameterized via deep neural networks. To test our method against conventional TO approaches implemented in commercial software, we evaluate it on four problems involving the minimization of dissipated power in Stokes flow.
  arXiv  Detail & Related papers  (2024-08-07T01:01:35Z)
• The Complexity of Optimizing Atomic Congestion [14.845310803203724]
  Atomic congestion games are a classic topic in network design, routing, and algorithmic game theory. We show that the problem remains highly intractable even on extremely simple networks. We conclude by extending our analysis towards the (even more challenging) min-max variant of the problem.
  arXiv  Detail & Related papers  (2023-12-15T21:31:30Z)
• Multi-Grid Tensorized Fourier Neural Operator for High-Resolution PDEs [93.82811501035569]
  We introduce a new data efficient and highly parallelizable operator learning approach with reduced memory requirement and better generalization. MG-TFNO scales to large resolutions by leveraging local and global structures of full-scale, real-world phenomena. We demonstrate superior performance on the turbulent Navier-Stokes equations where we achieve less than half the error with over 150x compression.
  arXiv  Detail & Related papers  (2023-09-29T20:18:52Z)
• Slow Invariant Manifolds of Singularly Perturbed Systems via Physics-Informed Machine Learning [0.0]
  We present a physics-informed machine-learning (PIML) approach for the approximation of slow invariant manifold (SIMs) of singularly perturbed systems. We show that the proposed PIML scheme provides approximations, of equivalent or even higher accuracy, than those provided by other traditional GSPT-based methods. A comparison of the computational costs between symbolic, automatic and numerical approximation of the required derivatives in the learning process is also provided.
  arXiv  Detail & Related papers  (2023-09-14T14:10:22Z)
• Deep learning applied to computational mechanics: A comprehensive review, state of the art, and the classics [77.34726150561087]
  Recent developments in artificial neural networks, particularly deep learning (DL), are reviewed in detail. Both hybrid and pure machine learning (ML) methods are discussed. History and limitations of AI are recounted and discussed, with particular attention at pointing out misstatements or misconceptions of the classics.
  arXiv  Detail & Related papers  (2022-12-18T02:03:00Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Efficient Micro-Structured Weight Unification and Pruning for Neural Network Compression [56.83861738731913]
  Deep Neural Network (DNN) models are essential for practical applications, especially for resource limited devices. Previous unstructured or structured weight pruning methods can hardly truly accelerate inference. We propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration.
  arXiv  Detail & Related papers  (2021-06-15T17:22:59Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)

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.