# Linear Readout of Neural Manifolds with Continuous Variables

arXiv: https://arxiv.org/abs/2603.10956 · HTML: https://mlsanity.com/paper/2603.10956/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2026.

## Built on by (most cited first, 1 of 1)

- [Two Speeds of Learning: A Representation-Readout Decomposition of Grokking and Double Descent](https://mlsanity.com/paper/2605.27078/) (2026)

## Abstract (arXiv)

Brains and artificial neural networks compute with continuous variables such as object position or stimulus orientation. However, the complex variability in neural responses makes it difficult to link internal representational structure to task performance. We develop a statistical-mechanical theory of regression capacity that relates linear decoding efficiency of continuous variables to geometric properties of neural manifolds. Our theory handles complex neural variability and applies to real data, revealing increasing capacity for decoding object position and size along the monkey visual stream.