{"slug": "sqs-bayesian-dnn-compression-through-sparse-quantized-sub-distributions", "title": "SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions", "summary": "Researchers propose SQS, a Bayesian method that unifies pruning and quantization for deep neural network compression by modeling weights with sparse quantized sub-distributions, achieving higher compression rates while preserving accuracy. The method targets deployment on resource-constrained devices, addressing limitations of existing approaches that apply pruning or quantization separately.", "body_md": "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", "url": "https://wpnews.pro/news/sqs-bayesian-dnn-compression-through-sparse-quantized-sub-distributions", "canonical_source": "https://aiflash.com/news/116164/", "published_at": "2026-09-09 07:30:02+00:00", "updated_at": "2026-09-09 07:58:15.621541+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": [], "alternates": {"html": "https://wpnews.pro/news/sqs-bayesian-dnn-compression-through-sparse-quantized-sub-distributions", "markdown": "https://wpnews.pro/news/sqs-bayesian-dnn-compression-through-sparse-quantized-sub-distributions.md", "text": "https://wpnews.pro/news/sqs-bayesian-dnn-compression-through-sparse-quantized-sub-distributions.txt", "jsonld": "https://wpnews.pro/news/sqs-bayesian-dnn-compression-through-sparse-quantized-sub-distributions.jsonld"}}