# Teaching with IMPACT

## TL;DR

This paper introduces a new teaching-based learning framework where a knowledgeable teacher guides learners through curriculum phases, enabling efficient learning of complex concepts that are otherwise unlearnable in standard settings.

## Contribution

It proposes a novel curriculum-based framework with theoretical and empirical support, demonstrating how teachers can help learners acquire complex concepts efficiently.

## Key findings

- Framework enables learning of unlearnable concepts in PAC setting
- Provides algorithms for learning complex concepts via curriculum guidance
- Supports learning complex concepts on top of simpler ones

## Abstract

Like many problems in AI in their general form, supervised learning is computationally intractable. We hypothesize that an important reason humans can learn highly complex and varied concepts, in spite of the computational difficulty, is that they benefit tremendously from experienced and insightful teachers. This paper proposes a new learning framework that provides a role for a knowledgeable, benevolent teacher to guide the process of learning a target concept in a series of "curricular" phases or rounds. In each round, the teacher's role is to act as a moderator, exposing the learner to a subset of the available training data to move it closer to mastering the target concept. Via both theoretical and empirical evidence, we argue that this framework enables simple, efficient learners to acquire very complex concepts from examples. In particular, we provide multiple examples of concept classes that are known to be unlearnable in the standard PAC setting along with provably efficient algorithms for learning them in our extended setting. A key focus of our work is the ability to learn complex concepts on top of simpler, previously learned, concepts---a direction with the potential of creating more competent artificial agents.