AdONE Seminar: Prof. Benjamin Moseley (Carnegie Mellon University)

New Directions on Algorithms with Predictions

Prof. Moseley during his presentation

This talk will discuss a model for augmenting algorithms with useful predictions to improve algorithm performance. The model ensures predictions are formally learnable and robust. Learnability guarantees that predictions can be efficiently constructed from past data. Robustness formally ensures a prediction is robust to modest changes in the problem input. This talk will discuss new directions for using predictions in algorithm design.