Prospective Learning: Principled Extrapolation to the Future

TL;DR

This paper introduces the concept of prospective learning, focusing on adapting to dynamic, partially predictable futures, which better models real-world scenarios than traditional static or adversarial assumptions.

Contribution

It formulates prospective learning as a new framework for understanding and developing algorithms capable of handling evolving data distributions over time.

Findings

Prospective learning is more challenging than retrospective learning.

It better models real-world evolving scenarios.

Studying prospective learning can improve AI solutions.

Abstract

Learning is a process which can update decision rules, based on past experience, such that future performance improves. Traditionally, machine learning is often evaluated under the assumption that the future will be identical to the past in distribution or change adversarially. But these assumptions can be either too optimistic or pessimistic for many problems in the real world. Real world scenarios evolve over multiple spatiotemporal scales with partially predictable dynamics. Here we reformulate the learning problem to one that centers around this idea of dynamic futures that are partially learnable. We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning. We argue that prospective learning more accurately characterizes many real world problems that (1) currently stymie existing artificial intelligence solutions and/or (2) lack adequate explanations for how natural intelligences solve them. Thus, studying prospective learning will lead to deeper insights and solutions to currently vexing challenges in both natural and artificial intelligences.