Optimizing Human Learning

TL;DR

This paper introduces a novel approach to optimize spaced repetition schedules for human learning by modeling it as an optimal control problem, resulting in an algorithm that improves memorization efficiency based on memory recall probabilities.

Contribution

It presents a new framework using marked temporal point processes and formulates the scheduling as an optimal control problem, leading to a scalable online algorithm for improved learning.

Findings

The optimal review schedule aligns with recall probability.

The Memorize algorithm outperforms existing methods in experiments.

Effective on both synthetic and real Duolingo data.

Abstract

Spaced repetition is a technique for efficient memorization which uses repeated, spaced review of content to improve long-term retention. Can we find the optimal reviewing schedule to maximize the benefits of spaced repetition? In this paper, we introduce a novel, flexible representation of spaced repetition using the framework of marked temporal point processes and then address the above question as an optimal control problem for stochastic differential equations with jumps. For two well-known human memory models, we show that the optimal reviewing schedule is given by the recall probability of the content to be learned. As a result, we can then develop a simple, scalable online algorithm, Memorize, to sample the optimal reviewing times. Experiments on both synthetic and real data gathered from Duolingo, a popular language-learning online platform, show that our algorithm may be able to help learners memorize more effectively than alternatives.