Not All Explanations for Deep Learning Phenomena Are Equally Valuable

TL;DR

This paper critiques the focus on isolated deep learning phenomena, arguing they often lack real-world relevance but can still help refine general theories, and offers recommendations for more pragmatic research approaches.

Contribution

It challenges the value of studying isolated phenomena without real-world evidence and advocates for using them to improve broad deep learning theories.

Findings

Many phenomena lack evidence in real-world applications

Current research often treats phenomena as isolated puzzles

Proposes practical guidelines for future deep learning research

Abstract

Developing a better understanding of surprising or counterintuitive phenomena has constituted a significant portion of deep learning research in recent years. These include double descent, grokking, and the lottery ticket hypothesis -- among many others. Works in this area often develop ad hoc hypotheses attempting to explain these observed phenomena on an isolated, case-by-case basis. This position paper asserts that, in many prominent cases, there is little evidence to suggest that these phenomena appear in real-world applications and these efforts may be inefficient in driving progress in the broader field. Consequently, we argue against viewing them as isolated puzzles that require bespoke resolutions or explanations. However, despite this, we suggest that deep learning phenomena do still offer research value by providing unique settings in which we can refine our broad explanatory theories of more general deep learning principles. This position is reinforced by analyzing the research outcomes of several prominent examples of these phenomena from the recent literature. We revisit the current norms in the research community in approaching these problems and propose practical recommendations for future research, aiming to ensure that progress on deep learning phenomena is well aligned with the ultimate pragmatic goal of progress in the broader field of deep learning.