CSQ: Centered Symmetric Quantization for Extremely Low Bit Neural Networks
Recent advances in quantized neural networks (QNNs) are closing the performance gap with the full precision neural networks. However at very low precision (i.e., $\le 3$-bits), QNNs often still suffer significant performance degradation. The conventional uniform symmetric quantization scheme allocates unequal numbers of positive and negative quantization levels. We show that this asymmetry in the number of positive and negative quantization levels can result in significant quantization error and performance degradation at low precision. We propose and analyze a quantizer called centered symmetric quantizer (CSQ), which preserves the symmetry of latent distribution by providing equal representations to the negative and positive sides of the distribution. We also propose a novel method to efficiently map CSQ to binarized neural network hardware using bitwise operations. Our analyses and experimental results using state-of-the-art quantization methods on ImageNet and CIFAR-10 show the importance of using CSQ for weight in place of the conventional quantization scheme at extremely low-bit precision (2$\sim$3 bits).
Code (0)
등록된 구현이 없습니다.
Tasks
QuantizationSimilar Papers 제목 키워드 기반
SYQ: Learning Symmetric Quantization For Efficient Deep Neural Networks
Inference for state-of-the-art deep neural networks is computationally expensive, making them difficult to deploy on constrained hardware environments. An efficient way to reduce this complexity is to quantize the weight…
QuantizationMRQ:Support Multiple Quantization Schemes through Model Re-Quantization
Despite the proliferation of diverse hardware accelerators (e.g., NPU, TPU, DPU), deploying deep learning models on edge devices with fixed-point hardware is still challenging due to complex model quantization and conver…
modelQuantizationHow to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
This paper investigates three different parameterizations of asymmetric uniform quantization for quantization-aware training: (1) scale and offset, (2) minimum and maximum, and (3) beta and gamma. We perform a comprehens…
QuantizationAFPQ: Asymmetric Floating Point Quantization for LLMs
Large language models (LLMs) show great performance in various tasks, but face deployment challenges from limited memory capacity and bandwidth. Low-bit weight quantization can save memory and accelerate inference. Altho…
QuantizationLSQ+: Improving low-bit quantization through learnable offsets and better initialization
Unlike ReLU, newer activation functions (like Swish, H-swish, Mish) that are frequently employed in popular efficient architectures can also result in negative activation values, with skewed positive and negative ranges.…
Image ClassificationQuantization