1. Mirror descent view for neural network quantization;Ajanthan;AISTATS,2021
2. Ternary neural networks for resource-efficient AI applications
3. Proxquant: Quantized neural networks via proximal operators;Bai;ICLR,2019
4. Estimating or propagating gradients through stochastic neurons for conditional computation;Bengio,2013
5. Xnor-net++: Improved binary neural networks;Bulat,2019