Efficient Mathematical Methods for the Optimization of Large and Complex Systems
Abstract
This project studies complex large-scale optimization problems, numerical algorithm, and applications in machine learning, optimal control, transportation, and power systems. A summary of some of our results developed during the last performance period is provided below:Projection-free online convex optimization: We considered structured online convex optimization (OCO) with bandit feedback, where either the loss function is smooth or the constraint set is strongly convex. Projection- free methods are among the most popular and computationally efficient algorithms for solving this problem, mainly due to their ability to handle convex constraints appearing in machine learning for which computing projections is often impractical in high-dimensional settings. Despite the improved regret bound results for the full-information setting where the gradients of the functions are readily available, it remains unclear whether simple projection-free zero-order algorithms become more efficient for structured OCO problems in the case when multiple function values can be sampled at each time instance.
Document Details
- Document Type
- Technical Report
- Publication Date
- Aug 17, 2021
- Accession Number
- AD1146057
Entities
People
- Javad Lavaei
Organizations
- University of California Regents