arXiv Artificial Intelligence

SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

6 hours ago 10.09.2026 07:00 👁 2 views
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions

Quick summary

arXiv:2510.08999v2 Announce Type: replace-cross Abstract: 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

Key takeaways

  • arXiv:2510.08999v2 Announce Type: replace-cross Abstract: 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.

Why it matters

The importance of “SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗