Session 5
Deterministic convex optimization basics. Gradient descent. Smooth vs. non-smooth convex problems.
Session 6
Deterministic convex optimization continued.
Session 7
Review and practice.
Session 8
Mid-course test and reviews.
Session 9
Non-convex stochastic optimization.
Session 10
Non-convex stochastic optimization continued.
Session 11
Projection-free methods.
Session 12
Decentralized optimization.
COURSE OUTLINESession 3
ML models continued: optimization framework.
Session 4
Implementing regularization in regression and matrix decompositions.
Session 2
ML models: linear regression, logistic regression, generalized linear models. Regularization. SVM model. Neural net model.
Session 1
Course outline. Recap of fundamental mathematical concepts: derivatives, convexity, matrix computations.
Session 13
Optimization for visual dimensionality reduction.
Session 14
Review and practice.
Session 15
Final test and reviews.