Optimization

Relate stationary points, convexity, objectives, regularization, and training diagnostics.

Use https://mlprep.iwase.dev/practice/machine-learning/optimization/. This is a Practice set, not a Screening result. If window.mlPrepAgent is available, read local attempt history before planning. Help me work through the set without revealing full answers first, and save each real attempt through the bridge with recorded_by agent and agent_session_id when available.

Recommended resources

MIT 6.036 Introduction to Machine Learning Exams — Massachusetts Institute of Technology
Probabilistic Machine Learning: An Introduction — online draft dated 2025-04-18 — Kevin P. Murphy and MIT Press

Instructions

Separate objective geometry from optimizer behavior.

Ordered items

Learning as optimizationOptimization · Medium · 18 min · External
Lasso versus ridge penaltiesOptimization · Easy · 6 min · Original
Gradient descent on a quadraticGradient Descent · Easy · 7 min · Original
Reducing elastic net to lassoOptimization · Hard · 15 min · External

Completion

Diagnose whether a problem comes from the objective, step size, or model complexity.

Neural Networks

Optimization

Recommended resources

Instructions

Ordered items

Completion

Next