SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
SQS unifies weight pruning and low-bit quantization via Bayesian variational learning, compressing Llama3.2 and Qwen2.5 at higher rates with comparable accuracy.
SQS introduces a unified Bayesian variational framework performing simultaneous pruning and low-bit quantization, using a spike-and-slab prior for sparsity and Gaussian Mixture Models to model quantized weights. The authors derive an efficient approximation for the intractable objective and provide a consistency result for the variational approach. Experiments on ResNet, BERT-base, Llama3.2, and Qwen2.5 show higher compression rates than prior baselines with comparable performance drops.
- Spike-and-slab prior induces sparsity; GMMs model low-bit quantized weights.
- Higher compression rates than existing baselines with comparable accuracy loss.
- Validated on ResNet, BERT-base, Llama3.2, and Qwen2.5 models.
- Includes theoretical consistency result for the variational approximation.
Full article162 words · extracted from huggingface.co · click to collapse
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 framework for simultaneous pruning and low-bit quantization via Bayesian variational learning (\method), which achieves higher compression rates than prior baselines while maintaining comparable performance. The key idea is to employ a spike-and-slab prior to induce sparsity and model quantized weights using Gaussian Mixture Models (GMMs) to enable low-bit precision. Due to the intractability of the objective involving spike-and-slab priors with GMMs, we derive an efficient approximation that facilitates effective compression with minimal accuracy loss. In theory, we provide a consistent result for our proposed variational approach to a sparse and quantized deep neural network. Extensive experiments on compressing ResNet, BERT-base, Llama3.2, and Qwen2.5 models show that our method achieves higher compression rates than a line of existing methods with comparable performance drops. Project page: https://comeusr.github.io/SQS_Webpage.
Text extracted automatically; images, tables and formatting may be missing. Original: https://huggingface.co/papers/2510.08999