Capacity-Constrained Continual Learning
This addresses a foundational gap in understanding learning under capacity constraints for AI agents, though it is a first step and incremental in theoretical study.
The paper tackles the problem of how agents with limited memory and compute resources should allocate capacity for optimal performance in continual learning, focusing on a capacity-constrained linear-quadratic-Gaussian sequential prediction problem and deriving a solution with optimal allocation across sub-problems in steady state.
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.