# Why Neural Networks Work

arXiv: https://arxiv.org/abs/2211.14632 · HTML: https://mlsanity.com/paper/2211.14632/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 29 references that are in the map.
- First posted on arXiv 26 Nov 2022.

## Builds on (most cited first, 11 of 11)

- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Reconciling modern machine learning practice and the bias-variance trade-off](https://mlsanity.com/paper/1812.11118/) (2018)
- [Spectrally-normalized margin bounds for neural networks](https://mlsanity.com/paper/1706.08498/) (2017)
- [On Lazy Training in Differentiable Programming](https://mlsanity.com/paper/1812.07956/) (2018)
- [Deep learning: a statistical viewpoint](https://mlsanity.com/paper/2103.09177/) (2021)
- [The Principles of Deep Learning Theory](https://mlsanity.com/paper/2106.10165/) (2021)
- [Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs](https://mlsanity.com/paper/2003.00152/) (2020)
- [Analysis of dropout learning regarded as ensemble learning](https://mlsanity.com/paper/1706.06859/) (2017)
- [Expressivity of expand-and-sparsify representations](https://mlsanity.com/paper/2006.03741/) (2020)

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

- [Sequencing the Neurome: Towards Scalable Exact Parameter Reconstruction of Black-Box Neural Networks](https://mlsanity.com/paper/2409.19138/) (2024)

## Abstract (arXiv)

We argue that many properties of fully-connected feedforward neural networks (FCNNs), also called multi-layer perceptrons (MLPs), are explainable from the analysis of a single pair of operations, namely a random projection into a higher-dimensional space than the input, followed by a sparsification operation. For convenience, we call this pair of successive operations expand-and-sparsify following the terminology of Dasgupta. We show how expand-and-sparsify can explain the observed phenomena that have been discussed in the literature, such as the so-called Lottery Ticket Hypothesis, the surprisingly good performance of randomly-initialized untrained neural networks, the efficacy of Dropout in training and most importantly, the mysterious generalization ability of overparameterized models, first highlighted by Zhang et al. and subsequently identified even in non-neural network models by Belkin et al.