|Speaker :||Lorenzo Maggi|
|Nokia Bell Labs France|
|Time:||11:00 am - 12:00 pm|
Bayesian optimization proves to be useful when our goal is to i) optimize an unknown function, that we can learn by sampling ii) our sample budget is (very) limited iii) we can afford (potentially) heavy computations in between two consecutive samples.
Slides will be largely inspired by https://arxiv.org/abs/2012.08469.