What is a local minimum in Gradient Descent?

Updated May 16, 2026

Short answer

A local minimum is a point where the function is lower than nearby points but not necessarily global lowest.

Deep explanation

Gradient Descent can get stuck in local minima in non-convex functions. These are points where gradient is zero but better solutions may exist elsewhere.

Real-world example

Neural networks training with multiple error valleys.

Common mistakes

  • Assuming GD always finds global minimum.

Follow-up questions

  • What is global minimum?
  • How to escape local minima?

More Gradient Descent interview questions

View all →