paper-with-me

Papers

Regularized linear autoencoders recover the principal components, eventually

2020-07-13 · NeurIPS 2020 12 · Xuchan Bao, James Lucas, Sushant Sachdeva, Roger Grosse

Our understanding of learning input-output relationships with neural nets has improved rapidly in recent years, but little is known about the convergence of the underlying representations, even in the simple case of linear autoencoders (LAEs). We show that when trained with proper regularization, LAEs can directly learn the optimal representation -- ordered, axis-aligned principal components. We analyze two such regularization schemes: non-uniform $\ell_2$ regularization and a deterministic variant of nested dropout [Rippel et al, ICML' 2014]. Though both regularization schemes converge to the optimal representation, we show that this convergence is slow due to ill-conditioning that worsens with increasing latent dimension. We show that the inefficiency of learning the optimal representation is not inevitable -- we present a simple modification to the gradient descent update that greatly speeds up convergence empirically.

📄 PDF Abstract BibTeX arXiv:2007.06731

Code (1)

XuchanBao/linear-ae 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Loss Landscapes of Regularized Linear Autoencoders

2019-01-23 · Daniel Kunin, Jonathan M. Bloom, Aleksandrina Goeva, Cotton Seed

Autoencoders are a deep learning model for representation learning. When trained to minimize the distance between the data and its reconstruction, linear autoencoders (LAEs) learn the subspace spanned by the top principa…

DecoderRepresentation Learning

From Principal Subspaces to Principal Components with Linear Autoencoders

2018-04-26 · Elad Plaut

The autoencoder is an effective unsupervised learning model which is widely used in deep learning. It is well known that an autoencoder with a single fully-connected hidden layer, a linear activation function and a squar…

Dimensionality Reduction

Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder

2026-01-27 · Qipeng Zhan, Zhuoping Zhou, Zexuan Wang, Li Shen arxiv

Autoencoders have long been considered a nonlinear extension of Principal Component Analysis (PCA). Prior studies have demonstrated that linear autoencoders (LAEs) can recover the ordered, axis-aligned principal componen…

Dimensionality Reduction

DIRESA, a distance-preserving nonlinear dimension reduction technique based on regularized autoencoders

2024-04-28 · Geert De Paepe, Lesley De Cruz

In meteorology, finding similar weather patterns or analogs in historical datasets can be useful for data assimilation, forecasting, and postprocessing. In climate science, analogs in historical and climate projection da…

Climate ProjectionDimensionality Reduction

The dynamics of representation learning in shallow, non-linear autoencoders

2022-01-06 · Maria Refinetti, Sebastian Goldt

Autoencoders are the simplest neural network for unsupervised learning, and thus an ideal framework for studying feature learning. While a detailed understanding of the dynamics of linear autoencoders has recently been o…

Representation Learning