Sharp error bounds for imbalanced classification: how many examples in the minority class?

• URL: http://arxiv.org/abs/2310.14826v2
• Date: Tue, 16 Apr 2024 13:25:38 GMT
• Title: Sharp error bounds for imbalanced classification: how many examples in the minority class?
• Authors: Anass Aghbalou, François Portier, Anne Sabourin,
• Abstract summary: Reweighting the loss function is a standard procedure allowing to equilibrate between the true positive and true negative rates within the risk measure. Despite significant theoretical work in this area, existing results do not adequately address a main challenge within the imbalanced classification framework. We present two contributions in the setting where the rare class probability approaches zero.
• Score: 6.74159270845872
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: When dealing with imbalanced classification data, reweighting the loss function is a standard procedure allowing to equilibrate between the true positive and true negative rates within the risk measure. Despite significant theoretical work in this area, existing results do not adequately address a main challenge within the imbalanced classification framework, which is the negligible size of one class in relation to the full sample size and the need to rescale the risk function by a probability tending to zero. To address this gap, we present two novel contributions in the setting where the rare class probability approaches zero: (1) a non asymptotic fast rate probability bound for constrained balanced empirical risk minimization, and (2) a consistent upper bound for balanced nearest neighbors estimates. Our findings provide a clearer understanding of the benefits of class-weighting in realistic settings, opening new avenues for further research in this field.

Related papers

• Rethinking generalization of classifiers in separable classes scenarios and over-parameterized regimes [0.0]
  We show that in separable classes scenarios the proportion of "bad" global minima diminishes exponentially with the number of training data n. We propose a model for the density distribution of the true error, yielding learning curves that align with experiments on MNIST and CIFAR-10.
  arXiv  Detail & Related papers  (2024-10-22T10:12:57Z)
• Probabilistic Contrastive Learning for Long-Tailed Visual Recognition [78.70453964041718]
  Longtailed distributions frequently emerge in real-world data, where a large number of minority categories contain a limited number of samples. Recent investigations have revealed that supervised contrastive learning exhibits promising potential in alleviating the data imbalance. We propose a novel probabilistic contrastive (ProCo) learning algorithm that estimates the data distribution of the samples from each class in the feature space.
  arXiv  Detail & Related papers  (2024-03-11T13:44:49Z)
• Shrinking Class Space for Enhanced Certainty in Semi-Supervised Learning [59.44422468242455]
  We propose a novel method dubbed ShrinkMatch to learn uncertain samples. For each uncertain sample, it adaptively seeks a shrunk class space, which merely contains the original top-1 class. We then impose a consistency regularization between a pair of strongly and weakly augmented samples in the shrunk space to strive for discriminative representations.
  arXiv  Detail & Related papers  (2023-08-13T14:05:24Z)
• Optimal variance-reduced stochastic approximation in Banach spaces [114.8734960258221]
  We study the problem of estimating the fixed point of a contractive operator defined on a separable Banach space. We establish non-asymptotic bounds for both the operator defect and the estimation error.
  arXiv  Detail & Related papers  (2022-01-21T02:46:57Z)
• Divide-and-Conquer Hard-thresholding Rules in High-dimensional Imbalanced Classification [1.0312968200748118]
  We study the impact of imbalance class sizes on the linear discriminant analysis (LDA) in high dimensions. We show that due to data scarcity in one class, referred to as the minority class, the LDA ignores the minority class yielding a maximum misclassification rate. We propose a new construction of a hard-conquering rule based on a divide-and-conquer technique that reduces the large difference between the misclassification rates.
  arXiv  Detail & Related papers  (2021-11-05T07:44:28Z)
• Statistical Theory for Imbalanced Binary Classification [8.93993657323783]
  We show that optimal classification performance depends on certain properties of class imbalance that have not previously been formalized. Specifically, we propose a novel sub-type of class imbalance, which we call Uniform Class Imbalance. These results provide some of the first meaningful finite-sample statistical theory for imbalanced binary classification.
  arXiv  Detail & Related papers  (2021-07-05T03:55:43Z)
• Risk Bounds and Rademacher Complexity in Batch Reinforcement Learning [36.015585972493575]
  This paper considers batch Reinforcement Learning (RL) with general value function approximation. The excess risk of Empirical Risk Minimizer (ERM) is bounded by the Rademacher complexity of the function class. Fast statistical rates can be achieved by using tools of local Rademacher complexity.
  arXiv  Detail & Related papers  (2021-03-25T14:45:29Z)
• On Focal Loss for Class-Posterior Probability Estimation: A Theoretical Perspective [83.19406301934245]
  We first prove that the focal loss is classification-calibrated, i.e., its minimizer surely yields the Bayes-optimal classifier. We then prove that the focal loss is not strictly proper, i.e., the confidence score of the classifier does not match the true class-posterior probability. Our proposed transformation significantly improves the accuracy of class-posterior probability estimation.
  arXiv  Detail & Related papers  (2020-11-18T09:36:52Z)
• Imbalanced Image Classification with Complement Cross Entropy [10.35173901214638]
  We study the study of cross entropy which mostly ignores output scores on incorrect classes. This work discovers that predicted probabilities on incorrect classes improves the prediction accuracy for imbalanced image classification. The proposed loss makes the ground truth class overwhelm the other classes in terms of softmax probability.
  arXiv  Detail & Related papers  (2020-09-04T13:46:24Z)
• A One-step Approach to Covariate Shift Adaptation [82.01909503235385]
  A default assumption in many machine learning scenarios is that the training and test samples are drawn from the same probability distribution. We propose a novel one-step approach that jointly learns the predictive model and the associated weights in one optimization.
  arXiv  Detail & Related papers  (2020-07-08T11:35:47Z)
• Provable tradeoffs in adversarially robust classification [96.48180210364893]
  We develop and leverage new tools, including recent breakthroughs from probability theory on robust isoperimetry. Our results reveal fundamental tradeoffs between standard and robust accuracy that grow when data is imbalanced.
  arXiv  Detail & Related papers  (2020-06-09T09:58:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.