KAI XIAO

In this paper we study a variety of novel online algorithm problems inspired by the game Mousehunt. We consider a number of basic models that approximate the game, and we provide solutions to these models using Markov Decision Processes, deterministic online algorithms, and randomized online algorithms. We analyze these solutions' performance by deriving results on their competitive ratios... In robust machine learning, I am currently interested in developing more robust and secure machine learning models. If machine learning models are to be deployed in the real world, we want these models to be reliable; however, the existence of adversarial examples - impercetibly modified inputs that fool state-of-the-art classifiers - raises concerns about the brittleness of such models. A major focus of my research has been on effective methods of formally verifying the robustness of these models... We introduce 3DB: an extendable, unified framework for testing and debugging vision models using..