Variational Rank Reduction Autoencoders for Generative

• URL: http://arxiv.org/abs/2509.08515v1
• Date: Wed, 10 Sep 2025 11:45:40 GMT
• Title: Variational Rank Reduction Autoencoders for Generative
• Authors: Alicia Tierz, Jad Mounayer, Beatriz Moya, Francisco Chinesta,
• Abstract summary: Generative thermal design for complex geometries is fundamental in many areas of engineering.<n>It faces two main challenges: the high computational cost of high-fidelity simulations and the limitations of conventional generative models.<n>We propose a hybrid framework that combines Variational Rank-Reduction Autoencoders (VRRAEs) with Deep Operator Networks (DeepONets)
• Score: 2.099922236065961
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generative thermal design for complex geometries is fundamental in many areas of engineering, yet it faces two main challenges: the high computational cost of high-fidelity simulations and the limitations of conventional generative models. Approaches such as autoencoders (AEs) and variational autoencoders (VAEs) often produce unstructured latent spaces with discontinuities, which restricts their capacity to explore designs and generate physically consistent solutions. To address these limitations, we propose a hybrid framework that combines Variational Rank-Reduction Autoencoders (VRRAEs) with Deep Operator Networks (DeepONets). The VRRAE introduces a truncated SVD within the latent space, leading to continuous, interpretable, and well-structured representations that mitigate posterior collapse and improve geometric reconstruction. The DeepONet then exploits this compact latent encoding in its branch network, together with spatial coordinates in the trunk network, to predict temperature gradients efficiently and accurately. This hybrid approach not only enhances the quality of generated geometries and the accuracy of gradient prediction, but also provides a substantial advantage in inference efficiency compared to traditional numerical solvers. Overall, the study underscores the importance of structured latent representations for operator learning and highlights the potential of combining generative models and operator networks in thermal design and broader engineering applications.

Related papers

• Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries [51.028432812178266]
  Transolver-3 is a new member of the Transolver family designed for high-fidelity physics simulations.<n>We show that Transolver-3 is capable of handling meshes with over 160 million cells, achieving impressive performance across three challenging simulation benchmarks.
  arXiv  Detail & Related papers  (2026-02-04T16:52:44Z)
• BladeSDF : Unconditional and Conditional Generative Modeling of Representative Blade Geometries Using Signed Distance Functions [4.188806282965805]
  This paper introduces a domain-specific implicit generative framework for turbine blade geometry using DeepSDF.<n>By integrating constraints, objectives, and performance metrics, this approach advances beyond traditional 2D-guided or unconstrained 3D pipelines.
  arXiv  Detail & Related papers  (2026-01-19T23:02:33Z)
• Reconstructing Multi-Scale Physical Fields from Extremely Sparse Measurements with an Autoencoder-Diffusion Cascade [38.28865883904372]
  Cascaded Sensing (Cas-Sensing) is a hierarchical reconstruction framework that integrates an autoencoder-diffusion cascade.<n>A conditional diffusion model, trained with a mask-cascade strategy, generates fine-scale details conditioned on large-scale structures.<n>Experiments on both simulation and real-world datasets demonstrate that Cas-Sensing generalizes well across varying sensor configurations and geometric boundaries.
  arXiv  Detail & Related papers  (2025-12-01T11:46:14Z)
• Autoencoder-based non-intrusive model order reduction in continuum mechanics [0.0]
  We propose a non-intrusive, Autoencoder-based framework for reduced-order modeling in continuum mechanics.<n>Our method integrates three stages: (i) an unsupervised Autoencoder compresses high-dimensional finite element solutions into a compact latent space, (ii) a supervised regression network maps problem parameters to latent codes, and (iii) an end-to-end surrogate reconstructs full-field solutions directly from input parameters.
  arXiv  Detail & Related papers  (2025-09-02T12:05:00Z)
• Revisiting the Privacy Risks of Split Inference: A GAN-Based Data Reconstruction Attack via Progressive Feature Optimization [49.32786615205064]
  Split Inference (SI) partitions computation between edge devices and the cloud to reduce latency and protect user privacy.<n>Recent advances in Data Reconstruction Attacks (DRAs) reveal that intermediate features exchanged in SI can be exploited to recover sensitive input data.<n>Existing DRAs are typically effective only on shallow models and fail to fully leverage semantic priors.<n>We propose a novel GAN-based DRA framework with Progressive Feature Optimization (PFO), which decomposes the generator into hierarchical blocks and incrementally refines intermediate representations to enhance the semantic fidelity of reconstructed images.
  arXiv  Detail & Related papers  (2025-08-28T10:00:39Z)
• STAR: Synthesis of Tailored Architectures [61.080157488857516]
  We propose a new approach for the synthesis of tailored architectures (STAR)<n>Our approach combines a novel search space based on the theory of linear input-varying systems, supporting a hierarchical numerical encoding into architecture genomes. STAR genomes are automatically refined and recombined with gradient-free, evolutionary algorithms to optimize for multiple model quality and efficiency metrics.<n>Using STAR, we optimize large populations of new architectures, leveraging diverse computational units and interconnection patterns, improving over highly-optimized Transformers and striped hybrid models on the frontier of quality, parameter size, and inference cache for autoregressive language modeling.
  arXiv  Detail & Related papers  (2024-11-26T18:42:42Z)
• Beyond the Kolmogorov Barrier: A Learnable Weighted Hybrid Autoencoder for Model Order Reduction [0.8021197489470758]
  We propose a learnable weighted hybrid autoencoder to overcome the Kolmogorov barrier.<n>We empirically find that our trained model has a sharpness thousands of times smaller compared to other models.
  arXiv  Detail & Related papers  (2024-10-23T00:04:26Z)
• Predicting Transonic Flowfields in Non-Homogeneous Unstructured Grids Using Autoencoder Graph Convolutional Networks [0.0]
  This paper focuses on addressing challenges posed by non-homogeneous unstructured grids, commonly used in Computational Fluid Dynamics (CFD) The core of our approach centers on geometric deep learning, specifically the utilization of graph convolutional network (GCN) The novel Autoencoder GCN architecture enhances prediction accuracy by propagating information to distant nodes and emphasizing influential points.
  arXiv  Detail & Related papers  (2024-05-07T15:18:21Z)
• Introducing a microstructure-embedded autoencoder approach for reconstructing high-resolution solution field data from a reduced parametric space [0.0]
  We develop a novel multi-fidelity deep learning approach that transforms low-fidelity solution maps into high-fidelity ones by incorporating parametric space information into a standard autoencoder architecture. This method's integration of parametric space information significantly reduces the need for training data to effectively predict high-fidelity solutions from low-fidelity ones.
  arXiv  Detail & Related papers  (2024-05-03T10:00:36Z)
• Symplectic Autoencoders for Model Reduction of Hamiltonian Systems [0.0]
  It is crucial to preserve the symplectic structure associated with the system in order to ensure long-term numerical stability. We propose a new neural network architecture in the spirit of autoencoders, which are established tools for dimension reduction. In order to train the network, a non-standard gradient descent approach is applied.
  arXiv  Detail & Related papers  (2023-12-15T18:20:25Z)
• Complexity Matters: Rethinking the Latent Space for Generative Modeling [65.64763873078114]
  In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion. In this study, we aim to shed light on this under-explored topic by rethinking the latent space from the perspective of model complexity.
  arXiv  Detail & Related papers  (2023-07-17T07:12:29Z)
• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Phase Retrieval using Expectation Consistent Signal Recovery Algorithm based on Hypernetwork [73.94896986868146]
  Phase retrieval is an important component in modern computational imaging systems. Recent advances in deep learning have opened up a new possibility for robust and fast PR. We develop a novel framework for deep unfolding to overcome the existing limitations.
  arXiv  Detail & Related papers  (2021-01-12T08:36:23Z)

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.