# Learnable Burst Quantization for Expressive and Efficient Spiking Neural Networks

arXiv: https://arxiv.org/abs/2604.25688 · HTML: https://mlsanity.com/paper/2604.25688/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 58 references that are in the map.
- First posted on arXiv 28 Apr 2026.

## Builds on (most cited first, 30 of 35)

- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Learned Step Size Quantization](https://mlsanity.com/paper/1902.08153/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks](https://mlsanity.com/paper/1706.02609/) (2017)
- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Residual Learning in Spiking Neural Networks](https://mlsanity.com/paper/2102.04159/) (2021)
- [Going Deeper With Directly-Trained Larger Spiking Neural Networks](https://mlsanity.com/paper/2011.05280/) (2020)
- [Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting](https://mlsanity.com/paper/2202.11946/) (2022)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [RMP-SNN: Residual Membrane Potential Neuron for Enabling Deeper High-Accuracy and Low-Latency Spiking Neural Network](https://mlsanity.com/paper/2003.01811/) (2020)
- [Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation](https://mlsanity.com/paper/2005.01807/) (2020)
- [Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks](https://mlsanity.com/paper/2103.00476/) (2021)
- [Enabling Spike-based Backpropagation for Training Deep Neural Network Architectures](https://mlsanity.com/paper/1903.06379/) (2019)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration](https://mlsanity.com/paper/2106.06984/) (2021)
- [Attention Spiking Neural Networks](https://mlsanity.com/paper/2209.13929/) (2022)
- [Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computing](https://mlsanity.com/paper/1603.08270/) (2016)
- [Integer-Valued Training and Spike-Driven Inference Spiking Neural Network for High-performance and Energy-efficient Object Detection](https://mlsanity.com/paper/2407.20708/) (2024)
- [GLIF: A Unified Gated Leaky Integrate-and-Fire Neuron for Spiking Neural Networks](https://mlsanity.com/paper/2210.13768/) (2022)
- [Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training](https://mlsanity.com/paper/2411.16061/) (2024)
- [Ternary Spike: Learning Ternary Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2312.06372/) (2023)
- [Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks](https://mlsanity.com/paper/1809.03142/) (2018)
- [Membrane Potential Batch Normalization for Spiking Neural Networks](https://mlsanity.com/paper/2308.08359/) (2023)
- [Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes](https://mlsanity.com/paper/2204.13271/) (2022)
- [RMP-Loss: Regularizing Membrane Potential Distribution for Spiking Neural Networks](https://mlsanity.com/paper/2308.06787/) (2023)
- [Real Spike: Learning Real-valued Spikes for Spiking Neural Networks](https://mlsanity.com/paper/2210.06686/) (2022)
- [Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks](https://mlsanity.com/paper/2210.06386/) (2022)
- [Inherent Redundancy in Spiking Neural Networks](https://mlsanity.com/paper/2308.08227/) (2023)
- [LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model](https://mlsanity.com/paper/2402.00411/) (2024)
- [STAA-SNN: Spatial-Temporal Attention Aggregator for Spiking Neural Networks](https://mlsanity.com/paper/2503.02689/) (2025)

## Abstract (arXiv)

Binary spikes provide only two neuronal output states per timestep, limiting the response capacity of spiking neural networks (SNNs) under short simulation horizons. Burst neurons expand this response space, but their threshold spacing is typically fixed before training, leaving layer-specific burst resolution outside end-to-end optimization. We propose Learnable Burst Quantization (LBQ), which formulates burst emission as saturated uniform quantization with a positive, layer-wise learnable step. ReLSG-ET, a rectified-linear surrogate gradient with exponential tails, provides gradient support throughout and beyond the active burst range, thereby enabling joint optimization of synaptic weights and burst resolution. At inference, LBQ absorbs each learned step into downstream weights and decomposes integer burst levels into binary bit planes, accumulating only the non-zero planes. This changes the synaptic accumulation count for a level S from S to operatornamepopcount(S). At two timesteps, LBQ achieves 97.45% on CIFAR-10 and 82.82% on CIFAR-100 with ResNet-20, and 73.67% on ImageNet-1K with ResNet-34. On CIFAR-10, it comes within 0.07 percentage points of the 97.52% ResNet-20 ANN reference; at Nmax=5, bit-plane execution reduces unary-equivalent synaptic accumulations by 40.52% relative to unary execution. Controlled ablations isolate the benefits of learned quantization and ReLSG-ET, while layer-wise analyses reveal selective burst allocation across network depth. Results on CIFAR10-DVS and DVS128-Gesture extend the evidence to event-driven recognition. LBQ therefore couples adaptive burst resolution and accurate inference with an algebraically equivalent bit-sparse synaptic execution path.