arXiv:2608.29867v1 Announce Type: new
Abstract: Autoencoders are widely used for nonlinear dimensionality reduction and manifold learning. While most common implementations rely on both nonlinear enc...
By Louen Pottier, Louis Lesueur, Anders Thorin
arXiv:2609.36806v1 Announce Type: new
Abstract: Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models. Eval...
By Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn, Ruben Ohana, Ira J. S. Shokar, Abouzar Ghasemi, Semih Akkurt, Rishikesh Ranade, Neil Ashton, Jan Kautz, Jean Kossaifi
arXiv:2609.36806v2 Announce Type: replace
Abstract: Modern engineering systems, from automobiles to aircraft, are designed by using precise, continuous parametric computer-aided design (CAD) models....
By Daniel Leibovici, Nikola Borislavov Kovachki, Dawon Ahn, Ruben Ohana, Ira J. S. Shokar, Abouzar Ghasemi, Semih Akkurt, Rishikesh Ranade, Neil Ashton, Jan Kautz, Jean Kossaifi
The paper investigates nonlinear dimensionality reduction for Bayesian optimisation (BO) by transforming high‑dimensional black‑box optimisation problems into a sequence of low‑dimensional latent‑space BO (LSBO) tasks. It extends earlier linear embedding approaches by using variational autoencoders (VAEs), deep metric loss, and adaptive retraining to better capture nonlinear structure, and couples LSBO with sequential domain reduction (SDR‑LSBO) to progressively narrow search domains. Experiments on GPU‑accelerated BoTorch with Matérn‑5/2 Gaussian‑process surrogates show that VAE‑based LSBO outperforms adaptive linear embeddings, and the authors provide a theoretical analysis of latent‑space error versus representation gap under PAC‑Bayes conditions.
By Luo Long, Coralia Cartis, Paz Fink Shustin
arXiv:2607. 10896v1 Announce Type: new Abstract: Small-data inverse design is challenging in engineering informatics when observations are heterogeneous, mixed-type, and constrained by physical relations among design variables.
By Giansalvo Cirrincione, Filippo Grassia
This paper introduces an adaptive surrogate modeling framework tailored for problems with extremely high‑dimensional spatio‑temporal outputs. The approach first reduces dimensionality by mapping outputs to a low‑dimensional latent space, then builds a surrogate model there, and finally employs a novel adaptive sampling strategy that balances exploration and exploitation to refine the surrogate with minimal expensive physics‑model runs. The method is validated on a thermo‑mechanical analysis of a gas turbine engine blade.
By Berkcan Kapusuzoglu, Shunsaku Matsumoto, Yoshitomo Miyagi, Daigo Watanabe, Sankaran Mahadevan