What are alternatives of Gradient Descent?

Question

Gradient Descent has a problem of Local Minima. We need run gradient descent exponential times for to find global minima.

Can anybody tell me about any alternatives of

Answer 1

Local minima is a property of the solution space, not the optimization method. It is a problem with neural networks in general. Convex methods, such as SVMs, have gained in popularity largely because of it.