# Radial-VCReg: More Informative Representation Learning Through Radial Gaussianization

arXiv: https://arxiv.org/abs/2602.14272 · HTML: https://mlsanity.com/paper/2602.14272/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 20 references that are in the map.
- First posted on arXiv 15 Feb 2026.

## Builds on (most cited first, 9 of 9)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Learning deep representations by mutual information estimation and maximization](https://mlsanity.com/paper/1808.06670/) (2018)
- [Learning Representations by Maximizing Mutual Information Across Views](https://mlsanity.com/paper/1906.00910/) (2019)
- [Whitening for Self-Supervised Representation Learning](https://mlsanity.com/paper/2007.06346/) (2020)
- [Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models](https://mlsanity.com/paper/2502.14819/) (2025)
- [Self-Supervised Learning with an Information Maximization Criterion](https://mlsanity.com/paper/2209.07999/) (2022)
- [Improving Pre-trained Self-Supervised Embeddings Through Effective Entropy Maximization](https://mlsanity.com/paper/2411.15931/) (2024)

## Built on by (most cited first, 4 of 4)

- [LpWM: A Case for Sparse Representations in World Models](https://mlsanity.com/paper/2608.22764/) (2026)
- [The Wristband Gaussian Loss: Deterministic, Composable Latents via a Sphere-Interval Decomposition](https://mlsanity.com/paper/2605.08749/) (2026)
- [Joint-Embedding Predictive Architecture for Sensor-based Activity Recognition](https://mlsanity.com/paper/2607.16350/) (2026)
- [Anisotropic Representations Improve Planning in JEPA World Models](https://mlsanity.com/paper/2609.37441/) (2026)

## Abstract (arXiv)

Self-supervised learning aims to learn maximally informative representations, but explicit information maximization is hindered by the curse of dimensionality. Existing methods like VCReg address this by regularizing first and second-order feature statistics, which cannot fully achieve maximum entropy. We propose Radial-VCReg, which augments VCReg with a radial Gaussianization loss that aligns feature norms with the Chi distribution-a defining property of high-dimensional Gaussians. We prove that Radial-VCReg transforms a broader class of distributions towards normality compared to VCReg and show on synthetic and real-world datasets that it consistently improves performance by reducing higher-order dependencies and promoting more diverse and informative representations.