Compressing the Gram Matrix for Learning Neural Networks in Polynomial Time

Surbhi Goel
Surbhi Goel

neural information processing systems, pp. 2189-2199, 2017.

Cited by: 0|Views7

Abstract:

We consider the problem of learning function classes computed by neural networks with various activations (e.g. ReLU or Sigmoid), a task believed to be intractable in the worst-case. A major open problem is to understand the minimal assumptions under which these classes admit efficient algorithms. In this work we show that a natural distr...More

Code:

Data:

Get fulltext within 24h
Bibtex
Your rating :
0

 

Tags
Comments