# Summary statistics of learning link changing neural representations to behavior

arXiv: https://arxiv.org/abs/2504.16920 · HTML: https://mlsanity.com/paper/2504.16920/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2025.

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

- [There Will Be a Scientific Theory of Deep Learning](https://mlsanity.com/paper/2604.21691/) (2026)
- [Learning Linear Regression with Low-Rank Tasks in-Context](https://mlsanity.com/paper/2510.04548/) (2025)
- [Stimulus symmetries can confound representational similarity analyses](https://mlsanity.com/paper/2605.21324/) (2026)
- [Width-Robust Learnability in Mean-Field Bayesian Neural Networks](https://mlsanity.com/paper/2607.05735/) (2026)

## Abstract (arXiv)

How can we make sense of large-scale recordings of neural activity across learning? Theories of neural network learning with their origins in statistical physics offer a potential answer: for a given task, there are often a small set of summary statistics that are sufficient to predict performance as the network learns. Here, we review recent advances in how summary statistics can be used to build theoretical understanding of neural network learning. We then argue for how this perspective can inform the analysis of neural data, enabling better understanding of learning in biological and artificial neural networks.