A Mean-field Optimal Control Formulation of Deep Learning
Date/Time:14 Mar 2019 16:00Venue: S17 #05-12 SR4Speaker: Li Qianxiao, National University of SingaporeA Mean-field Optimal Control Formulation of Deep LearningIn this talk, we discuss formulating, through a continuous-time approximation, deep supervised learning as a mean-field optimal control problem. We prove necessary conditions for optimality in the form of a mean-field Pontryagin’s maximum principle, as well as global characterizations of optimality using Hamilton-Jacobi-Bellman equations. Interesting learning algorithms derived from this approach will also be discussed.Add to calendar:
