Distribution Matching for Machine Teaching
This work addresses a specific bottleneck in machine teaching for scenarios where student parameters are undisclosed, representing an incremental improvement over prior methods.
The paper tackles the problem of machine teaching when the student's learning parameters are unknown, by proposing a distribution matching strategy that iteratively halves teaching cost to find optimal teaching examples. Experimental results demonstrate the effectiveness of this approach, though no specific numerical gains are provided.
Machine teaching is an inverse problem of machine learning that aims at steering the student learner towards its target hypothesis, in which the teacher has already known the student's learning parameters. Previous studies on machine teaching focused on balancing the teaching risk and cost to find those best teaching examples deriving the student model. This optimization solver is in general ineffective when the student learner does not disclose any cue of the learning parameters. To supervise such a teaching scenario, this paper presents a distribution matching-based machine teaching strategy. Specifically, this strategy backwardly and iteratively performs the halving operation on the teaching cost to find a desired teaching set. Technically, our strategy can be expressed as a cost-controlled optimization process that finds the optimal teaching examples without further exploring in the parameter distribution of the student learner. Then, given any a limited teaching cost, the training examples will be closed-form. Theoretical analysis and experiment results demonstrate this strategy.