# Deep ReLU Networks Have Surprisingly Few Activation Patterns

arXiv: https://arxiv.org/abs/1906.00904 · HTML: https://mlsanity.com/paper/1906.00904/

## Key facts

- Cited by 161 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2019.

## Built on by (most cited first, 30 of 161)

- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [Trustworthiness in Retrieval-Augmented Generation Systems: A Survey](https://mlsanity.com/paper/2409.10102/) (2024)
- [Neural Architecture Search for Spiking Neural Networks](https://mlsanity.com/paper/2201.10355/) (2022)
- [Random Neural Networks in the Infinite Width Limit as Gaussian Processes](https://mlsanity.com/paper/2107.01562/) (2021)
- [Provable Repair of Deep Neural Networks](https://mlsanity.com/paper/2104.04413/) (2021)
- [Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning](https://mlsanity.com/paper/2406.06158/) (2024)
- [Where Do We Stand with Implicit Neural Representations? A Technical and Performance Survey](https://mlsanity.com/paper/2411.03688/) (2024)
- [The Combinatorial Brain Surgeon: Pruning Weights That Cancel One Another in Neural Networks](https://mlsanity.com/paper/2203.04466/) (2022)
- [When Deep Learning Meets Polyhedral Theory: A Survey](https://mlsanity.com/paper/2305.00241/) (2023)
- [Hidden symmetries of ReLU networks](https://mlsanity.com/paper/2306.06179/) (2023)
- [Sharp bounds for the number of regions of maxout networks and vertices of Minkowski sums](https://mlsanity.com/paper/2104.08135/) (2021)
- [Consistent Counterfactuals for Deep Models](https://mlsanity.com/paper/2110.03109/) (2021)
- [Training invariances and the low-rank phenomenon: beyond linear networks](https://mlsanity.com/paper/2201.11968/) (2022)
- [Interpreting Neural Networks through the Polytope Lens](https://mlsanity.com/paper/2211.12312/) (2022)
- [AZ-NAS: Assembling Zero-Cost Proxies for Network Architecture Search](https://mlsanity.com/paper/2403.19232/) (2024)
- [Understanding the Feature Norm for Out-of-Distribution Detection](https://mlsanity.com/paper/2310.05316/) (2023)
- [Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions](https://mlsanity.com/paper/2210.07236/) (2022)
- [DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability](https://mlsanity.com/paper/2210.00364/) (2022)
- [Algorithmic Determination of the Combinatorial Structure of the Linear Regions of ReLU Neural Networks](https://mlsanity.com/paper/2207.07696/) (2022)
- [On the Number of Regions of Piecewise Linear Neural Networks](https://mlsanity.com/paper/2206.08615/) (2022)
- [Functional dimension of feedforward ReLU neural networks](https://mlsanity.com/paper/2209.04036/) (2022)
- [An Embedding of ReLU Networks and an Analysis of their Identifiability](https://mlsanity.com/paper/2107.09370/) (2021)
- [Scaling Up Exact Neural Network Compression by ReLU Stability](https://mlsanity.com/paper/2102.07804/) (2021)
- [Depth separation beyond radial functions](https://mlsanity.com/paper/2102.01621/) (2021)
- [Deep ReLU Networks Preserve Expected Length](https://mlsanity.com/paper/2102.10492/) (2021)
- [On the Expected Complexity of Maxout Networks](https://mlsanity.com/paper/2107.00379/) (2021)
- [Detection of out-of-distribution samples using binary neuron activation patterns](https://mlsanity.com/paper/2212.14268/) (2022)
- [Polyhedral Complex Extraction from ReLU Networks using Edge Subdivision](https://mlsanity.com/paper/2306.07212/) (2023)
- [Reliably-stabilizing piecewise-affine neural network controllers](https://mlsanity.com/paper/2111.07183/) (2021)
- [Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification](https://mlsanity.com/paper/2111.08922/) (2021)

## Abstract (arXiv)

The success of deep networks has been attributed in part to their expressivity: per parameter, deep networks can approximate a richer class of functions than shallow networks. In ReLU networks, the number of activation patterns is one measure of expressivity; and the maximum number of patterns grows exponentially with the depth. However, recent work has showed that the practical expressivity of deep networks - the functions they can learn rather than express - is often far from the theoretical maximum. In this paper, we show that the average number of activation patterns for ReLU networks at initialization is bounded by the total number of neurons raised to the input dimension. We show empirically that this bound, which is independent of the depth, is tight both at initialization and during training, even on memorization tasks that should maximize the number of activation patterns. Our work suggests that realizing the full expressivity of deep networks may not be possible in practice, at least with current methods.