Solving LASSO ($ {L}_{1} $ Regularized Least Squares) with Gradient Descent

1. Can you solve lasso with gradient descent?
2. What is gradient descent in deep learning?
3. Is lasso regression convex?

Can you solve lasso with gradient descent?

The two most popular variations of gradient descent that are used to solve lasso are coordinate descent and subgradient descent.

What is gradient descent in deep learning?

Gradient descent (GD) is an iterative first-order optimisation algorithm used to find a local minimum/maximum of a given function. This method is commonly used in machine learning (ML) and deep learning(DL) to minimise a cost/loss function (e.g. in a linear regression).

Is lasso regression convex?

The lasso solution is unique when rank(X) = p, because the criterion is strictly convex.