Unified Stochastic Framework for Neural Network Quantization and Pruning

Autor:	Zhang, Haoyu, Saab, Rayan
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Mathematics - Numerical Analysis Mathematics - Probability
Druh dokumentu:	Working Paper
Popis:	Quantization and pruning are two essential techniques for compressing neural networks, yet they are often treated independently, with limited theoretical analysis connecting them. This paper introduces a unified framework for post-training quantization and pruning using stochastic path-following algorithms. Our approach builds on the Stochastic Path Following Quantization (SPFQ) method, extending its applicability to pruning and low-bit quantization, including challenging 1-bit regimes. By incorporating a scaling parameter and generalizing the stochastic operator, the proposed method achieves robust error correction and yields rigorous theoretical error bounds for both quantization and pruning as well as their combination. Comment: 14 pages
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2412.18184 Zobrazit plný text záznamu View this record from Arxiv