2 papers
math.NA2020
An Alternative Thresholding Rule for Compressed Sensing
Jonathan Ashbrock
Compressed Sensing algorithms often make use of the hard thresholding operator to pass from dense vectors to their best s-sparse approximations. However, the output of the hard thr…
cs.LG2020
Stochastic Markov Gradient Descent and Training Low-Bit Neural Networks
Jonathan Ashbrock, Alexander M. Powell
The massive size of modern neural networks has motivated substantial recent interest in neural network quantization. We introduce Stochastic Markov Gradient Descent (SMGD), a discr…