Stochastic gradient descent §

= an iterative ⚙️ Algorithm for optimizing an objective function with suitable smoothness properties

How? §

1. Gradient determination: vector pointing in the direction of the greatest increase in a function
2. Gradient descent: move in the opposite direction of where the gradient points at
   • $\eta$: Learning rate, hyperparameter → chosen by algorithm designer

Example §

🔗 Links

🚶 Logistic Regression