Frame Quantization of Neural Networks
We present a post-training quantization algorithm with error estimates relying on ideas originating from frame theory. Specifically, we use first-order Sigma-Delta ($\Sigma\Delta$) quantization for finite unit-norm tight frames to quantize weight matrices and biases in a neural network. In our scenario, we derive an error bound between the original neural network and the quantized neural network in terms of step size and the number of frame elements. We also demonstrate how to leverage the redundancy of frames to achieve a quantized neural network with higher accuracy.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Generalized residual vector quantization for large scale data
Vector quantization is an essential tool for tasks involving large scale data, for example, large scale similarity search, which is crucial for content-based information retrieval and analysis. In this paper, we propose …
Information RetrievalQuantizationRetrievalR2Q: Towards Robust 2-Bit Large Language Models via Residual Refinement Quantization
The rapid progress of Large Language Models (LLMs) has brought substantial computational and memory demands, spurring the adoption of low-bit quantization. While 8-bit and 4-bit formats have become prevalent, extending q…
Question AnsweringTowards Accurate Post-training Network Quantization via Bit-Split and Stitching
Network quantization is essential for deploying deep models to IoT devices due to the high efficiency, no matter on special hardware like TPU or general hardware like CPU and GPU. Most existing quantization approaches re…
CPUGPUimage-classificationImage Classification+5Quantamination: Dynamic Quantization Leaks Your Data Across the Batch
Dynamic quantization emerged as a practical approach to increase the utilization and efficiency of the machine learning serving flow. Unlike static quantization, which applies quantization offline, dynamic quantization o…
A probabilistic framework for dynamic quantization
We propose a probabilistic framework for dynamic quantization of neural networks that allows for a computationally efficient input-adaptive rescaling of the quantization parameters. Our framework applies a probabilistic …
Quantization