Continuous Optimisation on Arshad Siddiqui

Optimisation using Gradient Descent

Mon, 01 Jan 0001 00:00:00 +0000

Gradient descent is an optimisation algorithm used to train ML and neural networks.

Trains ML models by minimising errors:

between predicted and actual results
by iteratively adjusting its parameters
moves step‑by‑step in the direction of the steepest decrease in the loss function, it helps ML models learn the best possible weights for better predictions

Mon, 01 Jan 0001 00:00:00 +0000

Optimisation with constraints (equalities/inequalities).

Mon, 01 Jan 0001 00:00:00 +0000

Transforms constrained problems into unconstrained ones using Lagrangians.

Mon, 01 Jan 0001 00:00:00 +0000

Convex objectives have a single global minimum, making optimisation reliable.