-
Gradient Descent Convergence - Prerequisites and Detailed Derivation
Understanding the convergence of gradient descent with a fixed step size and proving its rate of convergence for convex, differentiable functions.
-
Understanding Stochastic Gradient Descent (SGD)
A detailed guide to gradient descent variants, highlighting the mechanics, trade-offs, and practical insights of Stochastic Gradient Descent (SGD).
-
Gradient Descent - A Detailed Walkthrough
An in-depth exploration of gradient descent, including its convergence and step size considerations.
-
Empirical Risk Minimization (ERM)
Exploring Empirical Risk Minimization - Balancing approximation, estimation, and optimization errors to build effective supervised learning models.
-
Understanding the Supervised Learning Setup
An in-depth exploration of the supervised learning setup, covering key concepts like prediction functions, loss functions, risk evaluation, and the Bayes optimal predictor.