Searching for Low-Bit Weights in Quantized Neural Networks

Abstract

Quantized neural networks with low-bit weights and activations are attractive for developing AI accelerators. However, the quantization functions used in most conventional quantization methods are non-differentiable, which increases the optimization difficulty of quantized networks. Compared with full-precision parameters (i.e., 32-bit floating numbers), low-bit values are selected from a much smaller set. For example, there are only 16 possibilities in 4-bit space. Thus, we present to regard the discrete weights in an arbitrary quantized neural network as searchable variables, and utilize a differential method to search them accurately. In particular, each weight is represented as a probability distribution over the discrete value set. The probabilities are optimized during training and the values with the highest probability are selected to establish the desired quantized network. Experimental results on benchmarks demonstrate that the proposed method is able to produce quantized neural networks with higher performance over the state-of-the-art methods on both image classification and super-resolution tasks.

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Channel Pruning for Accelerating Very Deep Neural Networks
• AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
• Performance Guaranteed Network Acceleration via High-Order Residual Quantization
• Projection Convolutional Neural Networks for 1-bit CNNs via Discrete Back Propagation
• Cogradient Descent for Bilinear Optimization