Superpolynomial Lower Bounds for Learning One-Layer Neural Networks using Gradient Descent

Aravind Gollakota
Aravind Gollakota
Zhihan Jin
Zhihan Jin
Sushrut Karmalkar
Sushrut Karmalkar

ICML, pp. 3587-3596, 2020.

Cited by: 8|Views15
EI
Weibo:
We prove our lower bounds in the well-studied statistical query model of that captures most learning algorithms used in practice

Abstract:

We prove the first superpolynomial lower bounds for learning one-layer neural networks with respect to the Gaussian distribution using gradient descent. We show that any classifier trained using gradient descent with respect to square-loss will fail to achieve small test error in polynomial time given access to samples labeled by a one-...More

Code:

Data:

0
Your rating :
0

 

Tags
Comments