# ESPN: Extremely Sparse Pruned Networks

arXiv: https://arxiv.org/abs/2006.15741 · HTML: https://mlsanity.com/paper/2006.15741/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2020.

## Built on by (most cited first, 3 of 3)

- [Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate](https://mlsanity.com/paper/2402.02769/) (2024)
- [Selective Network Linearization for Efficient Private Inference](https://mlsanity.com/paper/2202.02340/) (2022)
- [Neural Network Panning: Screening the Optimal Sparse Network Before Training](https://mlsanity.com/paper/2209.13378/) (2022)

## Abstract (arXiv)

Deep neural networks are often highly overparameterized, prohibiting their use in compute-limited systems. However, a line of recent works has shown that the size of deep networks can be considerably reduced by identifying a subset of neuron indicators (or mask) that correspond to significant weights prior to training. We demonstrate that an simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks. Our algorithm represents a hybrid approach between single shot network pruning methods (such as SNIP) with Lottery-Ticket type approaches. We validate our approach on several datasets and outperform several existing pruning approaches in both test accuracy and compression ratio.