在线学习会因目标偏移导致性能下降，本文提出修正方法使其效果媲美离线学习。
Characterizing and Correcting Effective Target Shift in Online Learning
- 通过目标修正补偿在线学习中的有效目标偏移
- 在CIFAR-10和CORe50上，修正后性能优于使用真实目标
- 适用于持续学习中分布变化的场景
在线学习从数据流中获取知识是智能的核心特征，但现代机器学习系统在分布漂移下常表现不佳。本文研究核回归中在线与离线学习的关系，推导出在线核回归的闭式解，发现其等价于使用被偏移的、不准确的目标输出进行离线回归。反向而言，通过针对教学信号中的有效偏移进行目标修正，可使基于核的在线学习证明性地达到与离线版本相同的预测器。我们推导了该目标修正的闭式表达及可逐次应用的迭代形式。在CIFAR-10和CORe50图像分类任务上的实验表明，在持续学习设置中，使用迭代修正目标的在线随机梯度下降优于使用真实目标的学习。本工作为分析和改进非平稳环境下的在线学习提供了基础框架。
原文摘要 · Abstract (English)
Online learning from a stream of data is a defining feature of intelligence, yet modern machine learning systems often struggle in this setting, especially under distributional shift. To understand its basic properties, we study the relationship between online and offline learning in the context of kernel regression. We derive a closed-form expression for the function learned by online kernel regression, revealing that online kernel regression is equivalent to offline regression with shifted, inaccurate target outputs. Conversely, we show that by compensating for this effective shift in the teaching signal through target correction, online kernel-based learning can provably learn the same predictor as its offline counterpart. We derive both a closed-form expression for this target correction and an iterative form that can be applied sequentially. Applying this framework to image classification tasks on CIFAR-10 and CORe50, we show that online stochastic gradient descent with iteratively corrected targets outperforms learning with the true targets in continual learning settings. This work therefore provides a basic framework for analyzing and improving online learning in non-stationary environments.
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。