Optimization algorithms used in ML

Published:

A pedagogical implementation of the following optimization algorithms used to trained ML models:

  • Gradient descent
  • Steepest descent
  • Gradient descent with momentum
  • Nesterov Accelerated Gradient Descent
  • AdaGrad
  • AdaDelta
  • RMSProp
  • Adam
  • Newton’s method
  • Constrained Newton’s method
  • Barrier method (interior-point methods)