# Proof of a perfect platonic representation hypothesis

arXiv: https://arxiv.org/abs/2507.01098 · HTML: https://mlsanity.com/paper/2507.01098/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 1 Jul 2025.

## Builds on (most cited first, 13 of 13)

- [Neural Tangent Kernel: Convergence and Generalization in Neural Networks](https://mlsanity.com/paper/1806.07572/) (2018)
- [Exact solutions to the nonlinear dynamics of learning in deep linear neural networks](https://mlsanity.com/paper/1312.6120/) (2013)
- [Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability](https://mlsanity.com/paper/2103.00065/) (2021)
- [The Platonic Representation Hypothesis](https://mlsanity.com/paper/2405.07987/) (2024)
- [Feature Learning in Infinite-Width Neural Networks](https://mlsanity.com/paper/2011.14522/) (2020)
- [On the Origin of Implicit Regularization in Stochastic Gradient Descent](https://mlsanity.com/paper/2101.12176/) (2021)
- [Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced](https://mlsanity.com/paper/1806.00900/) (2018)
- [Implicit Gradient Regularization](https://mlsanity.com/paper/2009.11162/) (2020)
- [The Tunnel Effect: Building Data Representations in Deep Neural Networks](https://mlsanity.com/paper/2305.19753/) (2023)
- [Understanding the Emergence of Multimodal Representation Alignment](https://mlsanity.com/paper/2502.16282/) (2025)
- [Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent](https://mlsanity.com/paper/2402.07193/) (2024)
- [Formation of Representations in Neural Networks](https://mlsanity.com/paper/2410.03006/) (2024)
- [Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning](https://mlsanity.com/paper/2505.12387/) (2025)

## Built on by (most cited first, 8 of 8)

- [There Will Be a Scientific Theory of Deep Learning](https://mlsanity.com/paper/2604.21691/) (2026)
- [To Align or Not to Align: Strategic Multimodal Representation Alignment for Optimal Performance](https://mlsanity.com/paper/2511.12121/) (2025)
- [Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes](https://mlsanity.com/paper/2608.05000/) (2026)
- [ENIGMA: The Geometry of Reasoning and Alignment in Large-Language Models](https://mlsanity.com/paper/2510.11278/) (2025)
- [Toward Aristotelian Medical Representations: Backpropagation-Free Layer-wise Analysis for Interpretable Generalized Metric Learning on MedMNIST](https://mlsanity.com/paper/2604.06017/) (2026)
- [Representation Alignment Rests on Linear Structure](https://mlsanity.com/paper/2605.28870/) (2026)
- [Aristotelian Manifolds: Leveraging Platonic Perceptual Features for Backpropagation Free Rapid Concept Learning](https://mlsanity.com/paper/2608.20682/) (2026)
- [Platonic Task Arithmetic](https://mlsanity.com/paper/2610.00929/) (2026)

## Abstract (arXiv)

In this note, we elaborate on and explain in detail the proof given by Ziyin et al. (2025) of the ``perfect" Platonic Representation Hypothesis (PRH) for the embedded deep linear network model (EDLN). We show that if trained with the stochastic gradient descent (SGD), two EDLNs with different widths and depths and trained on different data will become Perfectly Platonic, meaning that every possible pair of layers will learn the same representation up to a rotation. Because most of the global minima of the loss function are not Platonic, that SGD only finds the perfectly Platonic solution is rather extraordinary. The proof also suggests at least six ways the PRH can be broken. We also show that in the EDLN model, the emergence of the Platonic representations is due to the same reason as the emergence of progressive sharpening. This implies that these two seemingly unrelated phenomena in deep learning can, surprisingly, have a common cause. Overall, the theory and proof highlight the importance of understanding emergent "entropic forces" due to the irreversibility of SGD training and their role in representation learning. The goal of this note is to be instructive while avoiding jargon and lengthy technical details.