Learning-Augmented Algorithms for Safety-Critical Systems

Making use of modern black-box AI tools such as deep reinforcement learning is potentially transformational for safety-critical systems such as data centers, the electricity grid, transportation, and beyond. However, such machine-learned algorithms typically do not have formal guarantees on their worst-case performance, stability, or safety. So while their performance may improve upon traditional approaches in “typical” cases, they may perform arbitrarily worse in scenarios where the training examples are not representative due to, for example, distribution shift. Thus, a challenging open question emerges: Is it possible to provide guarantees that allow black-box AI tools to be used in safety-critical applications? This talk will provide an overview of an emerging area in studying learning-augmented algorithms that seeks to answer this question in the affirmative. This talk will survey recent results in this area and describe applications of these results to the design of sustainable data centers and control of the smart grid.

Speaker: Adam Wierman, Caltech

Register at weblink to attend in person or online