# Pruning Increases Orderedness in Recurrent Computation

arXiv: https://arxiv.org/abs/2507.14747 · HTML: https://mlsanity.com/paper/2507.14747/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 11 references that are in the map.
- First posted on arXiv 19 Jul 2025.

## Builds on (most cited first, 5 of 5)

- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Proving the Lottery Ticket Hypothesis: Pruning is All You Need](https://mlsanity.com/paper/2002.00585/) (2020)
- [Seeing is Believing: Brain-Inspired Modular Training for Mechanistic Interpretability](https://mlsanity.com/paper/2305.08746/) (2023)
- [Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization](https://mlsanity.com/paper/2206.01198/) (2022)
- [The evolutionary origins of hierarchy](https://mlsanity.com/paper/1505.06353/) (2015)

## Abstract (arXiv)

Inspired by the prevalence of recurrent circuits in biological brains, we investigate the degree to which directionality is a helpful inductive bias for artificial neural networks. Taking directionality as topologically-ordered information flow between neurons, we formalise a perceptron layer with all-to-all connections (mathematically equivalent to a weight-tied recurrent neural network) and demonstrate that directionality, a hallmark of modern feed-forward networks, can be induced rather than hard-wired by applying appropriate pruning techniques. Across different random seeds our pruning schemes successfully induce greater topological ordering in information flow between neurons without compromising performance, suggesting that directionality is not a prerequisite for learning, but may be an advantageous inductive bias discoverable by gradient descent and sparsification.