On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
We investigate the convergence rates and data sample sizes required for training a machine learning model using a stochastic gradient descent (SGD) algorithm, where data points are sampled based on either their loss value or uncertainty value. These training methods are particularly relevant for active learning and data subset selection problems. For SGD with a constant step size update, we present convergence results for linear classifiers and linearly separable datasets using squared hinge loss and similar training loss functions. Additionally, we extend our analysis to more general classifiers and datasets, considering a wide range of loss-based sampling strategies and smooth convex training loss functions. We propose a novel algorithm called Adaptive-Weight Sampling (AWS) that utilizes SGD with an adaptive step size that achieves stochastic Polyak's step size in expectation. We establish convergence rate results for AWS for smooth convex training loss functions. Our numerical experiments demonstrate the efficiency of AWS on various datasets by using either exact or estimated loss values.
Code (1)
Tasks
Active LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Convergence of Uncertainty Sampling for Active Learning
Uncertainty sampling in active learning is heavily used in practice to reduce the annotation cost. However, there has been no wide consensus on the function to be used for uncertainty estimation in binary classification …
Active LearningBinary ClassificationClassificationMulti-class ClassificationUnderstanding Uncertainty Sampling
Uncertainty sampling is a prevalent active learning algorithm that queries sequentially the annotations of data samples which the current prediction model is uncertain about. However, the usage of uncertainty sampling ha…
Active LearningOnline Active Learning of Reject Option Classifiers
Active learning is an important technique to reduce the number of labeled examples in supervised learning. Active learning for binary classification has been well addressed in machine learning. However, active learning o…
Active LearningBinary ClassificationGeneral ClassificationImproving greedy core-set configurations for active learning with uncertainty-scaled distances
We scale perceived distances of the core-set algorithm by a factor of uncertainty and search for low-confidence configurations, finding significant improvements in sample efficiency across CIFAR10/100 and SVHN image clas…
Active Learningimage-classificationImage ClassificationUncertainty-aware Active Learning for Optimal Bayesian Classifier
For pool-based active learning, in each iteration a candidate training sample is chosen for labeling by optimizing an acquisition function. Expected Loss Reduction~(ELR) methods maximize the expected reduction in the cla…
Active LearningClassificationGeneral Classification