# Structured Kernel Regression VAE: A Computationally Efficient Surrogate for GP-VAEs in ICA

arXiv: https://arxiv.org/abs/2508.09721 · HTML: https://mlsanity.com/paper/2508.09721/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 35 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations](https://mlsanity.com/paper/1811.12359/) (2018)
- [Disentangling by Factorising](https://mlsanity.com/paper/1802.05983/) (2018)
- [Variational Autoencoders and Nonlinear ICA: A Unifying Framework](https://mlsanity.com/paper/1907.04809/) (2019)
- [Understanding disentangling in β-VAE](https://mlsanity.com/paper/1804.03599/) (2018)
- [Weakly-Supervised Disentanglement Without Compromises](https://mlsanity.com/paper/2002.02886/) (2020)
- [Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA](https://mlsanity.com/paper/2107.10098/) (2021)
- [Interventional Causal Representation Learning](https://mlsanity.com/paper/2209.11924/) (2022)
- [Weakly supervised causal representation learning](https://mlsanity.com/paper/2203.16437/) (2022)
- [CITRIS: Causal Identifiability from Temporal Intervened Sequences](https://mlsanity.com/paper/2202.03169/) (2022)
- [Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding](https://mlsanity.com/paper/2007.10930/) (2020)
- [Disentangled Sequential Autoencoder](https://mlsanity.com/paper/1803.02991/) (2018)
- [Gaussian Process Prior Variational Autoencoders](https://mlsanity.com/paper/1810.11738/) (2018)
- [Disentangling Identifiable Features from Noisy Data with Structured Nonlinear ICA](https://mlsanity.com/paper/2106.09620/) (2021)
- [Causal Component Analysis](https://mlsanity.com/paper/2305.17225/) (2023)
- [Learning Independent Features with Adversarial Nets for Non-linear ICA](https://mlsanity.com/paper/1710.05050/) (2017)
- [Longitudinal Variational Autoencoder](https://mlsanity.com/paper/2006.09763/) (2020)
- [Disentangled Variational Auto-Encoder for Semi-supervised Learning](https://mlsanity.com/paper/1709.05047/) (2017)
- [Decoupling Local and Global Representations of Time Series](https://mlsanity.com/paper/2202.02262/) (2022)
- [Half-VAE: An Encoder-Free VAE to Bypass Explicit Inverse Mapping](https://mlsanity.com/paper/2409.04140/) (2024)
- [Half-AVAE: Adversarial-Enhanced Factorized and Structured Encoder-Free VAE for Underdetermined Independent Component Analysis](https://mlsanity.com/paper/2506.07011/) (2025)

## Built on by (most cited first, 2 of 2)

- [PDGMM-VAE: A Variational Autoencoder with Adaptive Per-Dimension Gaussian Mixture Model Priors for Nonlinear ICA](https://mlsanity.com/paper/2603.23547/) (2026)
- [AR-Flow VAE: A Structured Autoregressive Flow Prior Variational Autoencoder for Unsupervised Blind Source Separation](https://mlsanity.com/paper/2603.14441/) (2026)

## Abstract (arXiv)

The interpretability of generative models is considered a key factor in demonstrating their effectiveness and controllability. The generated data are believed to be determined by latent variables that are not directly observable. Therefore, disentangling, decoupling, decomposing, causal inference, or performing Independent Component Analysis (ICA) in the latent variable space helps uncover the independent factors that influence the attributes or features affecting the generated outputs, thereby enhancing the interpretability of generative models. As a generative model, Variational Autoencoders (VAEs) combine with variational Bayesian inference algorithms. Using VAEs, the inverse process of ICA can be equivalently framed as a variational inference process. In some studies, Gaussian processes (GPs) have been introduced as priors for each dimension of latent variables in VAEs, structuring and separating each dimension from temporal or spatial perspectives, and encouraging different dimensions to control various attributes of the generated data. However, GPs impose a significant computational burden, resulting in substantial resource consumption when handling large datasets. Essentially, GPs model different temporal or spatial structures through various kernel functions. Structuring the priors of latent variables via kernel functions-so that different kernel functions model the correlations among sequence points within different latent dimensions-is at the core of achieving disentanglement in VAEs. The proposed Structured Kernel Regression VAE (SKR-VAE) leverages this core idea in a more efficient way, avoiding the costly kernel matrix inversion required in GPs. This research demonstrates that, while maintaining ICA performance, SKR-VAE achieves greater computational efficiency and significantly reduced computational burden compared to GP-VAE.