Almost Uniform Sampling From Neural Networks
Wu, Changlong, Santhanam, Narayana Prasad
Given a length $n$ sample from $\mathbb{R}^d$ 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 $\left(\frac{W}{2ekn}\right)^W$ for $W
Dec-10-2019
- Country:
- North America > United States
- California (0.14)
- Hawaii > Honolulu County
- Honolulu (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- North America > United States
- Genre:
- Research Report (0.50)
- Technology: