基于效用的扰动梯度下降：一种用于持续学习的优化器
Utility-based Perturbed Gradient Descent: An Optimizer for Continual Learning
AI总结：
针对持续学习中的灾难性遗忘与可塑性衰退问题，提出UPGD在线优化器，依据权重或特征效用保护有用部分并扰动低效用部分，实验表明其可减少遗忘并维持可塑性。
摘要：
现代表征学习方法在非平稳环境下往往难以快速适应，因为它们会遭受灾难性遗忘和可塑性衰退。这些问题阻碍学习器快速适应，原因是它们可能遗忘有用特征，或难以学习新特征。因此，这些方法在持续学习中变得无效。本文提出基于效用的扰动梯度下降（Utility-based Perturbed Gradient Descent，UPGD），这是一种非常适合持续学习智能体的在线学习算法。UPGD根据权重或特征的效用，保护有用的权重或特征免于遗忘，并扰动较无用的权重或特征。我们的实证结果表明，UPGD有助于减少遗忘并保持可塑性，使现代表征学习方法能够在持续学习中有效工作。
英文摘要：
Modern representation learning methods often struggle to adapt quickly under non-stationarity because they suffer from catastrophic forgetting and decaying plasticity. Such problems prevent learners from fast adaptation since they may forget useful features or have difficulty learning new ones. Hence, these methods are rendered ineffective for continual learning. This paper proposes Utility-based Perturbed Gradient Descent (UPGD), an online learning algorithm well-suited for continual learning agents. UPGD protects useful weights or features from forgetting and perturbs less useful ones based on their utilities. Our empirical results show that UPGD helps reduce forgetting and maintain plasticity, enabling modern representation learning methods to work effectively in continual learning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
