# SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

> Source: <https://aiflash.com/news/116164/>
> Published: 2026-09-09 07:30:02+00:00

Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing methods adopt weight pruning or low-bit quantization individually, often resulting in suboptimal compression rates to preserve acceptable performance drops. We introduce a unified