# Generalization Bounds of Spiking Neural Networks via Rademacher Complexity

arXiv: https://arxiv.org/abs/2605.02927 · HTML: https://mlsanity.com/paper/2605.02927/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 42 references that are in the map.
- First posted on arXiv 26 Apr 2026.

## Builds on (most cited first, 9 of 9)

- [Spectrally-normalized margin bounds for neural networks](https://mlsanity.com/paper/1706.08498/) (2017)
- [SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence](https://mlsanity.com/paper/2310.16620/) (2023)
- [Fast and energy-efficient neuromorphic deep learning with first-spike times](https://mlsanity.com/paper/1912.11443/) (2019)
- [Sparse Coding by Spiking Neural Networks: Convergence Theory and Computational Results](https://mlsanity.com/paper/1705.05475/) (2017)
- [Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders](https://mlsanity.com/paper/2404.04549/) (2024)
- [Bifurcation Spiking Neural Network](https://mlsanity.com/paper/1909.08341/) (2019)
- [On the Intrinsic Structures of Spiking Neural Networks](https://mlsanity.com/paper/2207.04876/) (2022)
- [On the Algorithmic Power of Spiking Neural Networks](https://mlsanity.com/paper/1803.10375/) (2018)
- [Generalization Bound for a General Class of Neural Ordinary Differential Equations](https://mlsanity.com/paper/2508.18920/) (2025)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) have garnered increasing attention as one of bio-inspired models due to their great potential in neuromorphic computing and sparse computation. Many practical algorithms and techniques have been developed; however, theoretical understandings of the generalization, that is, the extent to which SNNs perform well on unseen data, are far from clear. Recent advances disclosed an excitation-dependent and architecture-related generalization bound such that the Rademacher complexity of SNNs with stochastic firing can be upper bounded by an exponential function relative to the excitation probability and the architecture depth. In this paper, we theoretically investigate the generalization bounds of SNNs with several integration-and-fire schemes via Rademacher complexity. We recognize that the empirical Rademacher complexity of SNNs is close to the SNN configurations, which is exponential to the network depth and the maximum time duration of received spike sequences, superlinear and subquadratic to the network width, polynomial to the parameter norm, inverse-linear to the number of training samples, and independent of the computations within spiking neurons, achieving a more precise rate than conventional studies. Our theoretical results may support the scope of SNN theories and shed some insight into the development of SNNs.