Learning Distributions Generated by One-Layer ReLU Networks

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), pp. 8105-8115, 2019.

Cited by: 2|Bibtex|Views28|
EI
Keywords:
simple algorithmrectified gaussian distributionvector normsinfinity normnon-negative matrix factorization

Abstract:

We consider the problem of estimating the parameters of a d-dimensional rectified Gaussian distribution from i.i.d. samples. A rectified Gaussian distribution is defined by passing a standard Gaussian distribution through a one -layer ReLU neural network. We give a simple algorithm to estimate the parameters (i.e., the weight matrix and b...More

Code:

Data:

Your rating :
0

 

Tags
Comments