OPTIMAL BINARY QUANTIZATION FOR DEEP NEURAL NETWORKS
Quantizing weights and activations of deep neural networks results in significant improvement in inference efficiency at the cost of lower accuracy. A source of the accuracy gap between full precision and quantized models is the quantization error. In this work, we focus on the binary quantization, in which values are mapped to -1 and 1. We introduce several novel quantization algorithms: optimal 2-bits, optimal ternary, and greedy. Our quantization algorithms can be implemented efficiently on the hardware using bitwise operations. We present proofs to show that our proposed methods are optimal, and also provide empirical error analysis. We conduct experiments on the ImageNet dataset and show a reduced accuracy gap when using the proposed optimal quantization algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
Optimal Gradient Quantization Condition for Communication-Efficient Distributed Training
The communication of gradients is costly for training deep neural networks with multiple devices in computer vision applications. In particular, the growing size of deep learning models leads to higher communication over…
QuantizationLeast squares binary quantization of neural networks
Quantizing weights and activations of deep neural networks results in significant improvement in inference efficiency at the cost of lower accuracy. A source of the accuracy gap between full precision and quantized model…
QuantizationBinary Weight Multi-Bit Activation Quantization for Compute-in-Memory CNN Accelerators
Compute-in-memory (CIM) accelerators have emerged as a promising way for enhancing the energy efficiency of convolutional neural networks (CNNs). Deploying CNNs on CIM platforms generally requires quantization of network…
On the Needs for Rotations in Hypercubic Quantization Hashing
The aim of this paper is to endow the well-known family of hypercubic quantization hashing methods with theoretical guarantees. In hypercubic quantization, applying a suitable (random or learned) rotation after dimension…
Dimensionality ReductionQuantizationOptimal Quantization Using Scaled Codebook
We study the problem of quantizing N sorted, scalar datapoints with a fixed codebook containing K entries that are allowed to be rescaled. The problem is defined as finding the optimal scaling factor \alpha and the d…
Quantization