Unified Stochastic Framework for Neural Network Quantization and Pruning
This work addresses the need for efficient neural network compression for deployment in resource-constrained environments, offering a novel theoretical integration of quantization and pruning.
The paper tackles the problem of compressing neural networks by introducing a unified stochastic framework for post-training quantization and pruning, achieving robust error correction and providing rigorous theoretical error bounds for both techniques and their combination.
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.