Local Stability and Gaussian Smoothing of Quantized Neural Networks
Sergey Salishev, Anton Makarov, Oleg Granichin
cs.LG eess.SY math.OC
Abstract
We study Gaussian averaging as a smooth surrogate for quantized neural models. Under bounded local oscillation, we derive a local dimension-dependent bound on |f-g|, linking Gaussian smoothing to the stability analysis of discontinuous networks. We compute closed-form Gaussian averages of the rectified linear unit (ReLU) and sign activation functions, and illustrate the mechanism on a high-dimensional binary perceptron, where layer-preactivation aggregation under an explicit quantization-noise surrogate yields the Gaussian envelope used in inference-side smoothing and training-side smooth surrogate gradients.
Topics
Classified with taxonomy v2 on Wed, 2 Sept 2026.