# From Principal Subspaces to Principal Components with Linear Autoencoders

arXiv: https://arxiv.org/abs/1804.10253 · HTML: https://mlsanity.com/paper/1804.10253/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2018.

## Built on by (most cited first, 30 of 39)

- [Self-supervised Learning in Remote Sensing: A Review](https://mlsanity.com/paper/2206.13188/) (2022)
- [The Power of Contrast for Feature Learning: A Theoretical Analysis](https://mlsanity.com/paper/2110.02473/) (2021)
- [The dynamics of representation learning in shallow, non-linear autoencoders](https://mlsanity.com/paper/2201.02115/) (2022)
- [Geometric Autoencoders -- What You See is What You Decode](https://mlsanity.com/paper/2306.17638/) (2023)
- [Symmetry-Aware Autoencoders: s-PCA and s-nlPCA](https://mlsanity.com/paper/2111.02893/) (2021)
- [Probabilistic Robust Autoencoders for Outlier Detection](https://mlsanity.com/paper/2110.00494/) (2021)
- [Predicting waves in fluids with deep neural network](https://mlsanity.com/paper/2201.06628/) (2022)
- [A Mechanism for Producing Aligned Latent Spaces with Autoencoders](https://mlsanity.com/paper/2106.15456/) (2021)
- [InDiReCT: Language-Guided Zero-Shot Deep Metric Learning for Images](https://mlsanity.com/paper/2211.12760/) (2022)
- [Good Things Come in Pairs: Paired Autoencoders for Inverse Problems](https://mlsanity.com/paper/2505.06549/) (2025)
- [Neural Image Compression: Generalization, Robustness, and Spectral Biases](https://mlsanity.com/paper/2307.08657/) (2023)
- [Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping](https://mlsanity.com/paper/2309.16515/) (2023)
- [Sparse L1-Autoencoders for Scientific Data Compression](https://mlsanity.com/paper/2405.14270/) (2024)
- [DREAMS: Preserving both Local and Global Structure in Dimensionality Reduction](https://mlsanity.com/paper/2508.13747/) (2025)
- [Predicting Wind-Driven Spatial Deposition through Simulated Color Images using Deep Autoencoders](https://mlsanity.com/paper/2202.01762/) (2022)
- [The Persian Rug: solving toy models of superposition using large-scale symmetries](https://mlsanity.com/paper/2410.12101/) (2024)
- [Data-driven reduced order modeling of environmental hydrodynamics using deep autoencoders and neural ODEs](https://mlsanity.com/paper/2107.02784/) (2021)
- [Targeted collapse regularized autoencoder for anomaly detection: black hole at the center](https://mlsanity.com/paper/2306.12627/) (2023)
- [The Effect of SGD Batch Size on Autoencoder Learning: Sparsity, Sharpness, and Feature Learning](https://mlsanity.com/paper/2308.03215/) (2023)
- [Are We Using Autoencoders in a Wrong Way?](https://mlsanity.com/paper/2309.01532/) (2023)
- [Autoencoder-based non-intrusive model order reduction in continuum mechanics](https://mlsanity.com/paper/2509.02237/) (2025)
- [Optimal Stopping in Latent Diffusion Models](https://mlsanity.com/paper/2510.08409/) (2025)
- [PCAE: Learning Ordered Representations in Latent Space for Intrinsic Dimension Estimation via Principal Component Autoencoder](https://mlsanity.com/paper/2601.19179/) (2026)
- [An autoencoder compression approach for accelerating large-scale inverse problems](https://mlsanity.com/paper/2304.04781/) (2023)
- [Quantifying Credit Portfolio sensitivity to asset correlations with interpretable generative neural networks](https://mlsanity.com/paper/2309.08652/) (2023)
- [Principal Orthogonal Latent Components Analysis (POLCA Net)](https://mlsanity.com/paper/2410.07289/) (2024)
- [Enforcing Orderedness to Improve Feature Consistency](https://mlsanity.com/paper/2512.02194/) (2025)
- [Optimal Representation Size: High-Dimensional Analysis of Pretraining and Linear Probing](https://mlsanity.com/paper/2605.20105/) (2026)
- [Realization of Causal Representation Learning to Adjust Confounding Bias in Latent Space](https://mlsanity.com/paper/2211.08573/) (2022)
- [Autocodificadores Variacionales (VAE) Fundamentos Te'oricos y Aplicaciones](https://mlsanity.com/paper/2302.09363/) (2023)

## Abstract (arXiv)

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 squared error cost function trains weights that span the same subspace as the one spanned by the principal component loading vectors, but that they are not identical to the loading vectors. In this paper, we show how to recover the loading vectors from the autoencoder weights.