paper-with-me

Papers

Proper Latent Decomposition

2024-12-01 · Daniel Kelshaw, Luca Magri

In this paper, we introduce the proper latent decomposition (PLD) as a generalization of the proper orthogonal decomposition (POD) on manifolds. PLD is a nonlinear reduced-order modeling technique for compressing high-dimensional data into nonlinear coordinates. First, we compute a reduced set of intrinsic coordinates (latent space) to accurately describe a flow with fewer degrees of freedom than the numerical discretization. The latent space, which is geometrically a manifold, is inferred by an autoencoder. Second, we leverage tools from differential geometry to develop numerical methods for operating directly on the latent space; namely, a metric-constrained Eikonal solver for distance computations. With this proposed numerical framework, we propose an algorithm to perform PLD on the manifold. Third, we demonstrate results for a laminar flow case and the turbulent Kolmogorov flow. For the laminar flow case, we are able to identify a semi-analytical expression for the solution of Navier-Stokes; in the Kolmogorov flow case, we are able to identify a dominant mode that exhibits physical structures, which are compared with POD. This work opens opportunities for analyzing autoencoders and latent spaces, nonlinear reduced-order modeling and scientific insights into the structure of high-dimensional data.

📄 PDF Abstract BibTeX arXiv:2412.00785

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

On interpretability and proper latent decomposition of autoencoders

2022-11-15 · Luca Magri, Anh Khoa Doan

The dynamics of a turbulent flow tend to occupy only a portion of the phase space at a statistically stationary regime. From a dynamical systems point of view, this portion is the attractor. The knowledge of the turbulen…

Beyond Unfolding: Exact Recovery of Latent Convex Tensor Decomposition under Reshuffling

2018-05-22 · Chao Li, Mohammad Emtiyaz Khan, Zhun Sun, Gang Niu 외

Exact recovery of tensor decomposition (TD) methods is a desirable property in both unsupervised learning and scientific data analysis. The numerical defects of TD methods, however, limit their practical applications on …

Image SteganographyTensor Decomposition

Disentangling Disentanglement in Variational Autoencoders

2018-12-06 · Emile Mathieu, Tom Rainforth, N. Siddharth, Yee Whye Teh

We develop a generalisation of disentanglement in VAEs---decomposition of the latent representation---characterising it as the fulfilment of two factors: a) the latent encodings of the data having an appropriate level of…

ClusteringDisentanglement

Joint Modeling of a Matrix with Associated Text via Latent Binary Features

2012-12-01 · NeurIPS 2012 12 · Xianxing Zhang, Lawrence Carin

A new methodology is developed for joint analysis of a matrix and accompanying documents, with the documents associated with the matrix rows/columns. The documents are modeled with a focused topic model, inferring latent…

Exploring the latent space of diffusion models directly through singular value decomposition

2025-02-04 · Li Wang, Boyan Gao, Yanran Li, Zhao Wang 외

Despite the groundbreaking success of diffusion models in generating high-fidelity images, their latent space remains relatively under-explored, even though it holds significant promise for enabling versatile and interpr…

Denoising