paper-with-me

홈 › Papers

SPFQ: A Stochastic Algorithm and Its Error Analysis for Neural Network Quantization

2023-09-20 · Jinjie Zhang, Rayan Saab

Quantization is a widely used compression method that effectively reduces redundancies in over-parameterized neural networks. However, existing quantization techniques for deep neural networks often lack a comprehensive error analysis due to the presence of non-convex loss functions and nonlinear activations. In this paper, we propose a fast stochastic algorithm for quantizing the weights of fully trained neural networks. Our approach leverages a greedy path-following mechanism in combination with a stochastic quantizer. Its computational complexity scales only linearly with the number of weights in the network, thereby enabling the efficient quantization of large networks. Importantly, we establish, for the first time, full-network error bounds, under an infinite alphabet condition and minimal assumptions on the weights and input data. As an application of this result, we prove that when quantizing a multi-layer network having Gaussian weights, the relative square quantization error exhibits a linear decay as the degree of over-parametrization increases. Furthermore, we demonstrate that it is possible to achieve error bounds equivalent to those obtained in the infinite alphabet case, using on the order of a mere $\log\log N$ bits per weight, where $N$ represents the largest number of neurons in a layer.

📄 PDF Abstract BibTeX arXiv:2309.10975

Code (0)

등록된 구현이 없습니다.

Tasks

Quantization

Similar Papers 제목 키워드 기반

Unified Stochastic Framework for Neural Network Quantization and Pruning

2024-12-24 · Haoyu Zhang, Rayan Saab

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 framewor…

Quantization

Stochastic Learning Equation using Monotone Increasing Resolution of Quantization

2021-12-24 · Jinwuk Seok, Jeong-Si Kim

In this paper, we propose a quantized learning equation with a monotone increasing resolution of quantization and stochastic analysis for the proposed algorithm. According to the white noise hypothesis for the quantizati…

global-optimizationQuantization

Provable Post-Training Quantization: Theoretical Analysis of OPTQ and Qronos

2025-08-06 · Haoyu Zhang, Shihao Zhang, Ian Colbert, Rayan Saab arxiv

Post-training quantization (PTQ) has become a crucial tool for reducing the memory and compute costs of modern deep neural networks, including large language models (LLMs). Among PTQ algorithms, the OPTQ framework-also k…

Computational Efficiency

Quantization-Based Optimization: Alternative Stochastic Approximation of Global Optimization

2022-11-08 · Jinwuk Seok, Chang Sik Cho

In this study, we propose a global optimization algorithm based on quantizing the energy level of an objective function in an NP-hard problem. According to the white noise hypothesis for a quantization error with a dense…

global-optimizationQuantizationTraveling Salesman Problem

Quantization goes Polynomial

2017-10-31 · Giorgia Callegaro, Lucio Fiorin, Andrea Pallavicini

Quantization algorithms have been successfully adopted to option pricing in finance thanks to the high convergence rate of the numerical approximation. In particular, very recently, recursive marginal quantization has be…

Quantization