A recent, and fast-growing trend in Artificial Intelligence has focused on enhancing online algorithms with machine-learned predictions. Here, the online algorithm must leverage some additional information on the input so as to boost its performance. In this project we propose several research directions towards the efficient design and analysis of algorithms with predictions. Our main objective is to expand the known approaches so as to better study the power, but also the limitations of this class of algorithms, and obtain online algorithms which are proven to be theoretically efficient, but also perform well in practice.
This PhD research project has been submitted for a funding request to “Sorbonne Center for Artificial Intelligence (SCAI)”. The PhD candidate selected by the project leader will therefore participate in the project selection process (including a file and an interview) to obtain funding.