研究有限资源下智能体如何最优分配能力，提升持续学习性能。
Capacity-Constrained Continual Learning
- 基于有限容量的LQG序列预测问题，推导出理论解。
- 在稳态下实现子任务间的容量最优分配。
- 为资源受限学习提供首个系统性理论框架，适合算法设计者参考。
我们构建的所有智能体都受制于容量约束，因为内存和计算资源本质上是有限的。然而，关于有限容量的智能体应如何分配资源以实现最佳性能的研究却相对较少。本文通过研究一个简单但相关性强的持续学习问题——容量受限的线性-二次-高斯（LQG）序列预测问题，来探讨这一问题。在适当的条件下，我们推导出了该问题的解决方案。此外，对于可分解为一组子问题的情形，我们也展示了如何在稳态下对这些子问题进行容量的最优分配。我们认为，本文的结果是系统性地研究容量约束下学习问题的第一步。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。