Basic Information
Theory of Efficient Optimization Algorithms For Continuous Optimization Problems Arising in The Fields of Machine Learning And Big Data Analytics. Subjects Will Include# First-order Methods For Convex and Non-convex Optimization, Stochastic Optimization Methods For Convex and Non-convex Problems and Efficient Algorithms For Online Learning. Emphasis Will Be Given to The Development Of Efficient Algorithms With Rigorous Proofs of Their Computational Efficiency, As Well As The Development of Complementary Lower Bounds. Learning Outcomes# At The End of The Course The Student Will Know# 1. to Understand The Principles, and to Implememt a Large Variety Of Important and Central Optimization Algorithms in The Field of Machine Learning. 2. to Indenpendently Read and Understand Contemporary Litreature In The Fieald of Optimization Algorithms For Machine Learning. 3. to Embark On Academic Reasearch (both Theoretical and Practical) In The Field.
Faculty: Data and Decision Sciences
|Undergraduate Studies
|Graduate Studies
Pre-required courses
94411 - Probability (ie) or 94412 - Probability (advanced) or 104034 - Introduction to Probability H or 104222 - Probability Theory