Score: 2

Capacity-Constrained Continual Learning

Published: July 29, 2025 | arXiv ID: 2507.21479v1

By: Zheng Wen , Doina Precup , Benjamin Van Roy and more

BigTech Affiliations: Google Stanford University

Potential Business Impact:

Teaches computers to learn better with less memory.

Business Areas:
Machine Learning Artificial Intelligence, Data and Analytics, Software

Any agents we can possibly build are subject to capacity constraints, as memory and compute resources are inherently finite. However, comparatively little attention has been dedicated to understanding how agents with limited capacity should allocate their resources for optimal performance. The goal of this paper is to shed some light on this question by studying a simple yet relevant continual learning problem: the capacity-constrained linear-quadratic-Gaussian (LQG) sequential prediction problem. We derive a solution to this problem under appropriate technical conditions. Moreover, for problems that can be decomposed into a set of sub-problems, we also demonstrate how to optimally allocate capacity across these sub-problems in the steady state. We view the results of this paper as a first step in the systematic theoretical study of learning under capacity constraints.

Country of Origin
πŸ‡ΊπŸ‡Έ United States

Page Count
26 pages

Category
Computer Science:
Machine Learning (CS)