Computer scienceData scienceMachine learningIntroduction to deep learningOptimizers

Gradient descent with momentum

Momentum in non-convex optimization

Report a typo

In the context of non-convex optimization problems, how can the use of momentum in gradient descent with momentum affect the optimization process?

Select one option from the list

Momentum can lead to overshooting the optimal solution and hinder convergence.

Momentum increases the likelihood of getting stuck in shallow local minima.

Momentum guarantees convergence to the global minimum in non-convex optimization.

___

Create a free account to access the full topic