Algorithms with predictions, also known as learning-augmented algorithms, is an emerging field of research at the intersection of theoretical computer science and machine-learning. It looks to address the following question:
How to use imperfect predictions in a robust way – retaining worst-case guarantees of classic algorithms – yet achieve optimal performance when the predictions are accurate?
The workshop aims to support the community around this new topic with catching up with the latest results, discussing future directions and key open problems, and forming new cross-institutional collaborations.
Participants are expected to arrive in Lausanne on Sunday, May 1st in the evening, and depart on Friday, May 6th in the afternoon.
Each day of the workshop will consist of around 3 hours of talks and plenty of time for discussion and collaboration on open problems.
A detailed schedule is available here.