Capacity-Constrained Continual Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909710236516352 |
|---|---|
| author | Wen, Zheng Precup, Doina Van Roy, Benjamin Singh, Satinder |
| author_facet | Wen, Zheng Precup, Doina Van Roy, Benjamin Singh, Satinder |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21479 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Capacity-Constrained Continual Learning Wen, Zheng Precup, Doina Van Roy, Benjamin Singh, Satinder Machine Learning Artificial Intelligence Information Theory Systems and Control 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. |
| title | Capacity-Constrained Continual Learning |
| topic | Machine Learning Artificial Intelligence Information Theory Systems and Control |
| url | https://arxiv.org/abs/2507.21479 |