A Meta-learning Formulation of the Autoencoder Problem for Non-linear Dimensionality Reduction
A rapidly growing area of research is the use of machine learning approaches such as autoencoders for dimensionality reduction of data and models in scientific applications. We show that the canonical formulation of autoencoders suffers from several deficiencies that can hinder their performance. Using a meta-learning approach, we reformulate the autoencoder problem as a bi-level optimization procedure that explicitly solves the dimensionality reduction task. We prove that the new formulation corrects the identified deficiencies with canonical autoencoders, provide a practical way to solve it, and showcase the strength of this formulation with a simple numerical illustration.
Code (0)
등록된 구현이 없습니다.
Tasks
Dimensionality ReductionMeta-LearningSimilar Papers 제목 키워드 기반
Deep learning approach based on dimensionality reduction for designing electromagnetic nanostructures
In this paper, we demonstrate a computationally efficient new approach based on deep learning (DL) techniques for analysis, design, and optimization of electromagnetic (EM) nanostructures. We use the strong correlation a…
Dimensionality ReductionRecovery of Linear Components: Reduced Complexity Autoencoder Designs
Reducing dimensionality is a key preprocessing step in many data analysis applications to address the negative effects of the curse of dimensionality and collinearity on model performance and computational complexity, to…
Dimensionality ReductionVariable SelectionPCA-Boosted Autoencoders for Nonlinear Dimensionality Reduction in Low Data Regimes
Autoencoders (AE) provide a useful method for nonlinear dimensionality reduction but are ill-suited for low data regimes. Conversely, Principal Component Analysis (PCA) is data-efficient but is limited to linear dimensio…
Dimensionality ReductionAn autoencoder-based reduced-order model for eigenvalue problems with application to neutron diffusion
Using an autoencoder for dimensionality reduction, this paper presents a novel projection-based reduced-order model for eigenvalue problems. Reduced-order modelling relies on finding suitable basis functions which define…
Dimensionality ReductionProbabilistic Autoencoder
Principal Component Analysis (PCA) minimizes the reconstruction error given a class of linear models of fixed component dimensionality. Probabilistic PCA adds a probabilistic structure by learning the probability distrib…
Bayesian InferenceDenoisingImage GenerationImage Reconstruction+3