Nonlocal optimization of binary neural networks

04/05/2022
by   Amir Khoshaman, et al.
0

We explore training Binary Neural Networks (BNNs) as a discrete variable inference problem over a factor graph. We study the behaviour of this conversion in an under-parameterized BNN setting and propose stochastic versions of Belief Propagation (BP) and Survey Propagation (SP) message passing algorithms to overcome the intractability of their current formulation. Compared to traditional gradient methods for BNNs, our results indicate that both stochastic BP and SP find better configurations of the parameters in the BNN.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset