# Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening

arXiv: https://arxiv.org/abs/1808.08833 · HTML: https://mlsanity.com/paper/1808.08833/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2018.

## Built on by (most cited first, 6 of 6)

- [Reward prediction for representation learning and reward shaping](https://mlsanity.com/paper/2105.03172/) (2021)
- [Deep Deterministic Independent Component Analysis for Hyperspectral Unmixing](https://mlsanity.com/paper/2202.02951/) (2022)
- [Universal hidden monotonic trend estimation with contrastive learning](https://mlsanity.com/paper/2210.09817/) (2022)
- [Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks](https://mlsanity.com/paper/2402.12067/) (2024)
- [Slow Feature Analysis as Variational Inference Objective](https://mlsanity.com/paper/2506.00580/) (2025)
- [GANDiff FR: Hybrid GAN Diffusion Synthesis for Causal Bias Attribution in Face Recognition](https://mlsanity.com/paper/2508.11334/) (2025)

## Abstract (arXiv)

We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction. We provide experimental evidence that PowerSFA is able to extract meaningful and informative low-dimensional features in the case of (a) synthetic low-dimensional data, (b) ego-visual data, and also for (c) a general dataset for which symmetric non-temporal similarities between points can be defined.