Almost Uniform Sampling From Neural Networks

12/10/2019
by   Changlong Wu, et al.
0

Given a length n sample from R^d and a neural network with a fixed architecture with W weights, k neurons, linear threshold activation functions, and binary outputs on each neuron, we study the problem of uniformly sampling from all possible labelings on the sample corresponding to different choices of weights. We provide an algorithm that runs in time polynomial both in n and W such that any labeling appears with probability at least (W/2ekn)^W for W<n. For a single neuron, we also provide a random walk based algorithm that samples exactly uniformly.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset