LGMLNov 6, 2025

Forgetting is Everywhere

arXiv:2511.04666v1h-index: 47
Originality Highly original
AI Analysis

This provides a foundational framework for analyzing forgetting in general learning algorithms, which is incremental but addresses a long-standing challenge in machine learning.

The paper tackles the lack of a unified definition for forgetting in learning algorithms and proposes a theory that characterizes it as a loss of predictive information, validated through experiments across multiple learning settings.

A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge when adapting to new data. Addressing this problem requires a principled understanding of forgetting; yet, despite decades of study, no unified definition has emerged that provides insights into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution over future experiences, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's propensity to forget. To validate the theory, we design a comprehensive set of experiments that span classification, regression, generative modelling, and reinforcement learning. We empirically demonstrate how forgetting is present across all learning settings and plays a significant role in determining learning efficiency. Together, these results establish a principled understanding of forgetting and lay the foundation for analysing and improving the information retention capabilities of general learning algorithms.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes