Spiking Neural Networks (SNNs) offer an energy efficient alternative to conventional Artificial Neural Networks (ANNs) but typically still require a large number of parameters. This work introduces Linearized Bregman Iterations (LBI) as an optimizer for training SNNs, enforcing sparsity through iterative minimization of the Bregman distance and proximal soft thresholding updates. To improve convergence and generalization, we employ the AdaBreg optimizer, a momentum and bias corrected Bregman variant of Adam. Experiments on three established neuromorphic benchmarks, i.e. the Spiking Heidelberg Digits (SHD), the Spiking Speech Commands (SSC), and the Permuted Sequential MNIST (PSMNIST) datasets, show that LBI based optimization reduces the number of active parameters by about 50% while maintaining accuracy comparable to models trained with the Adam optimizer, demonstrating the potential of convex sparsity inducing methods for efficient neuromorphic learning.

翻译：[translated abstract in Chinese] 脉冲神经网络作为一种节能的替代方案，仍通常需要大量参数。本研究引入线性化Bregman迭代作为训练SNNs的优化器，通过迭代最小化Bregman距离和近端软阈值更新来实现稀疏性。为提升收敛性和泛化能力，我们采用AdaBreg优化器——一种结合动量和偏置校正的Adam的Bregman变体。在三个标准神经形态基准数据集（即Spiking Heidelberg Digits、Spiking Speech Commands和Permuted Sequential MNIST）上的实验表明，基于LBI的优化可在保持与Adam优化器训练模型相当精度的同时，将活跃参数数量减少约50%，这证明了凸稀疏诱导方法在高效神经形态学习中的潜力。