An Optimal Control Approach to Sequential Machine Teaching
[edit]
Proceedings of Machine Learning Research, PMLR 89:24952503, 2019.
Abstract
Given a sequential learning algorithm and a target model, sequential machine teaching aims to find the shortest training sequence to drive the learning algorithm to the target model. We present the first principled way to find such shortest training sequences. Our key insight is to formulate sequential machine teaching as a timeoptimal control problem. This allows us to solve sequential teaching by leveraging key theoretical and computational tools developed over the past 60 years in the optimal control community. Specifically, we study the Pontryagin Maximum Principle, which yields a necessary condition for opti mality of a training sequence. We present analytic, structural, and numerical implica tions of this approach on a case study with a leastsquares loss function and gradient de scent learner. We compute optimal train ing sequences for this problem, and although the sequences seem circuitous, we find that they can vastly outperform the best available heuristics for generating training sequences.
Related Material


