Characterizing and Correcting Effective Target Shift in Online Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Image ClassificationContinual LearningSimilar Papers 제목 키워드 기반
LTF: A Label Transformation Framework for Correcting Label Shift
Distribution shift is a major obstacle to the deployment of current deep learning models on real-world problems. Let $Y$ be the class label and $X$ the features. We focus on one type of distribution shift, \textit{ label…
Domain Adaptation for Time Series Under Feature and Label Shifts
Unsupervised domain adaptation (UDA) enables the transfer of models trained on source domains to unlabeled target domains. However, transferring complex time series models presents challenges due to the dynamic temporal …
Domain AdaptationTime SeriesTime Series AnalysisTransfer Learning+2Importance Weighting Correction of Regularized Least-Squares for Covariate and Target Shifts
In many real world problems, the training data and test data have different distributions. This situation is commonly referred as a dataset shift. The most common settings for dataset shift often considered in the litera…
regressionCorrecting sampling biases via importance reweighting for spatial modeling
In machine learning models, the estimation of errors is often complex due to distribution bias, particularly in spatial data such as those found in environmental studies. We introduce an approach based on the ideas of im…
Density EstimationTransfer Learning with Label Noise
Transfer learning aims to improve learning in target domain by borrowing knowledge from a related but different source domain. To reduce the distribution shift between source and target domains, recent methods have focus…
DenoisingTransfer Learning