Workshop on Learning-augmented Algorithms: Theory and Applications – June 14, 2024 – SIGMETRICS 2024
This workshop will cover recent results as well as new, emerging directions in the rapidly-advancing field of learning-augmented algorithms, also known as algorithms with predictions or algorithms with ML advice. This nascent area, at the intersection of TCS and ML, studies the interplay between ML and the design/analysis of algorithms with strict, provable performance guarantees. The workshop aims to provide a forum for recent developments in the design, analysis, and application of learning-augmented algorithms, including topics such as:
Design and analysis of algorithms with ML predictions: Exploring methods to use (possibly imperfect) predictions robustly, i.e., leveraging the predictions to enhance algorithmic performance while retaining the worst-case guarantees of classic algorithms. This also encompasses developing new ML techniques for learning predictions that are tailored to particular, challenging problem settings and applying data-driven approaches to optimize crucial algorithm parameters with learning-theoretic guarantees.
Applications: Evaluating the real-world impact of learning-augmented algorithms on various systems or problems, such as resource management in computing systems and networks, and control and optimization in cyberinfrastructure, cyber-physical systems, and smart grids.
This area has blossomed in recent years, both in terms of foundational theoretical results but also in terms of exciting applications across a broad range of settings, such as streaming algorithms, online scheduling, clustering, filtering, online matching, caching, system control, cloud computing, and many others. Some recent workshops/seminars on this topic include the Workshop on Algorithms with Predictions at EPFL in 2022, the Workshop on Algorithms with Predictions at STOC 2022 and STOC 2020, Machine Learning for Algorithms at FODSI, 2021, and the previous iteration of this workshop at SIGMETRICS 2023.
Workshop Chairs:
Spyros Angelopoulos, CNRS and Sorbonne University, spyros.angelopoulos@lip6.fr
Nicolas Christianson, Caltech, nchristianson@caltech.edu
Shaolei Ren, UC Riverside, sren@ece.ucr.edu
Bo Sun, University of Waterloo, bo.sun@uwaterloo.ca
Steering Committee:
Adam Wierman, Caltech, adamw@caltech.edu
Shahin Kamali, York University, kamalis@yorku.ca
Mohammad Hajiesmaili, UMass Amherst, hajiesmaili@cs.umass.edu