Towards Black-box Iterative Machine Teaching

10/21/2017
by   Weiyang Liu, et al.
0

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space teaching setting, where the teacher and the learner use different feature representations and the teacher can not fully observe the learner's model. In such scenario, we study how the teacher is still able to teach the learner to achieve a faster convergence rate than the traditional passive learning. We propose an active teacher model that can actively query the learner (i.e., make the learner take exams) for estimating the learner's status, and provide the sample complexity for both teaching and query, respectively. In the experiments, we compare the proposed active teacher with the omniscient teacher and verify the effectiveness of the active teacher model.

READ FULL TEXT

page 1

page 8

research
06/30/2022

When an Active Learner Meets a Black-box Teacher

Active learning maximizes the hypothesis updates to find those desired u...
research
10/31/2022

Iterative Teaching by Data Hallucination

We consider the problem of iterative machine teaching, where a teacher s...
research
02/04/2022

Time-Constrained Learning

Consider a scenario in which we have a huge labeled dataset D and a limi...
research
09/26/2022

Overcoming Referential Ambiguity in Language-Guided Goal-Conditioned Reinforcement Learning

Teaching an agent to perform new tasks using natural language can easily...
research
09/18/2019

On the Right Path: A Modal Logic for Supervised Learning

Formal learning theory formalizes the process of inferring a general res...
research
10/24/2019

Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models

Algorithmic machine teaching studies the interaction between a teacher a...
research
02/25/2018

Teacher Improves Learning by Selecting a Training Subset

We call a learner super-teachable if a teacher can trim down an iid trai...

Please sign up or login with your details

Forgot password? Click here to reset