Abstract: Solving high-dimensional optimization problems remains one of the key components in many applications, including design optimization, operations research, scientific exploration and so on. Traditionally these applications rely on heavy human experience to find good solutions and/or to tune the existing system for better performance. In this talk, I will cover our recent works in which deep neural networks, coupled with reinforcement learning and search methods, are used to learn heuristics of a complicated optimization problem, to achieve better performance than human experience. The application includes online job scheduling, neural architecture search, black-box optimization, and so on.
Bio: Yuandong Tian is a Research Scientist and Manager in Facebook AI Research, working on deep reinforcement learning in games and theoretical analysis of deep models. He led OpenGo, a super-human Go bot from Facebook AI. Prior to that, he was a Software Engineer/Researcher in Google Self-driving Car team during 2013-2014. He received Ph.D in Robotics Institute, Carnegie Mellon University on 2013, Bachelor and Master degree of Computer Science in Shanghai Jiao Tong University. He is the recipient of 2013 ICCV Marr Prize Honorable Mentions.