The Corvinus Centre for Operations Research (CCOR), the Corvinus Institute for Advanced Studies (CIAS), and the Institute of Operations and Decision Sciences invite you to the minicourse by Yurii Nesterov,
Modern Theory of First-Order Methods For Convex Optimization
Venue: Corvinus University, Building C
Date:
February 21. (Wednesday) 9:50-11:20 (Room C208)
February 21. (Wednesday) 13:40-15:10 (Room C417)
February 22. (Thursday) 9:50-11:20 (Room C104)
We would like to inform you that the lectures will be broadcast online. Please be aware that this broadcast will not utilize professional-grade equipment, and we appreciate your understanding that we cannot ensure the broadcast’s quality.
If you would like to join online, please send an e-mail to Anita Varga (anita dot varga at uni-corvinus dot hu) by February 21, 8:00.
Abstract
In this mini-course, we present the most important research directions related to development of the first-order methods for Convex Optimization. We start from discussing the main elements of Complexity Theory and corresponding Optimal Methods. After that, we present the Universal Methods, which can automatically adjust to the best problem class containing a particular problem instance. Finally, we demonstrate the advantages of an appropriate use of the internal structure of the problem in order to go far beyond the upper limits for efficiency of optimization schemes prescribed by the standard Complexity Theory.
The course consists of three lectures:
- Intrinsic Complexity of Convex Optimization
- Universal First-Order Methods
- Peeking into the Black Box: Smoothing Technique