Explore a 49-minute conference talk on learning-augmented online optimization presented by Ravi Kumar from Google Inc. at IPAM's EnCORE Workshop on Computational vs Statistical Gaps in Learning and Optimization. Recorded on February 26, 2024, at the Institute for Pure & Applied Mathematics (IPAM) at UCLA, this presentation delves into the intersection of machine learning and online optimization techniques. Gain insights into how learning algorithms can enhance traditional online optimization methods, potentially leading to more efficient and adaptive problem-solving approaches in various computational domains. Discover the latest research and developments in this field as Kumar shares his expertise on bridging the gap between computational and statistical aspects of learning and optimization.
Overview
Syllabus
Ravi Kumar - Learning-Augmented Online Optimization - IPAM at UCLA
Taught by
Institute for Pure & Applied Mathematics (IPAM)
Related Courses
-
A Perceptron Trio - Computational vs Statistical Gaps in Learning and Optimization
-
On the Hardness of Learning Under Symmetries
-
Learning from Dynamics in Linear Dynamical Systems
-
Distributed Optimization and Machine Learning
-
Testing Dependency of Databases - Lecture
-
Memory as a Lens to Understand Efficient Learning and Optimization
