paper-with-me

홈 › Papers

Local Stability and Gaussian Smoothing of Quantized Neural Networks

2026-07-22 · Sergey Salishev, Anton Makarov, Oleg Granichin arxiv

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.

📄 PDF Abstract BibTeX arXiv:2607.20153

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

LOTION: Smoothing the Optimization Landscape for Quantized Training

2025-10-09 · Mujin Kwun, Depen Morwani, Chloe Huangyuan Su, Stephanie Gil 외 arxiv

Optimizing neural networks for quantized objectives is fundamentally challenging because the quantizer is piece-wise constant, yielding zero gradients everywhere except at quantization thresholds where the derivative is …

Quantized Convolutional Neural Networks Through the Lens of Partial Differential Equations

2021-08-31 · NeurIPS Workshop DLDE 2021 12 · Ido Ben-Yair, Gil Ben Shalom, Moshe Eliasof, Eran Treister

Quantization of Convolutional Neural Networks (CNNs) is a common approach to ease the computational burden involved in the deployment of CNNs, especially on low-resource edge devices. However, fixed-point arithmetic is n…

Autonomous Drivingimage-classificationImage ClassificationNode Classification+1

Taylor Moment Expansion for Continuous-Discrete Gaussian Filtering and Smoothing

2020-01-08 · Zheng Zhao, Toni Karvonen, Roland Hostettler, Simo Särkkä

The paper is concerned with non-linear Gaussian filtering and smoothing in continuous-discrete state-space models, where the dynamic model is formulated as an It\^{o} stochastic differential equation (SDE), and the measu…

State Space Models

A Novel Evolution Strategy with Directional Gaussian Smoothing for Blackbox Optimization

2020-02-07 · Jiaxin Zhang, Hoang Tran, Dan Lu, Guannan Zhang

We propose an improved evolution strategy (ES) using a novel nonlocal gradient operator for high-dimensional black-box optimization. Standard ES methods with $d$-dimensional Gaussian smoothing suffer from the curse of di…

global-optimization

Training for Trustworthy Saliency Maps: Adversarial Training Meets Feature-Map Smoothing

2026-03-07 · Dipkamal Bhusal, Md Tanvirul Alam, Nidhi Rastogi arxiv

Gradient-based saliency methods such as Vanilla Gradient (VG) and Integrated Gradients (IG) are widely used to explain image classifiers, yet the resulting maps are often noisy and unstable, limiting their usefulness in …