Convergence of Uncertainty Sampling for Active Learning

• URL: http://arxiv.org/abs/2110.15784v1
• Date: Fri, 29 Oct 2021 13:51:30 GMT
• Title: Convergence of Uncertainty Sampling for Active Learning
• Authors: Anant Raj and Francis Bach
• Abstract summary: We propose an efficient uncertainty estimator for binary classification which we also extend to multiple classes. We provide theoretical guarantees for our algorithm under the influence of noise in the task of binary and multi-class classification.
• Score: 11.115182142203711
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 tasks and convergence guarantees of the corresponding active learning algorithms are not well understood. The situation is even more challenging for multi-category classification. In this work, we propose an efficient uncertainty estimator for binary classification which we also extend to multiple classes, and provide a non-asymptotic rate of convergence for our uncertainty sampling-based active learning algorithm in both cases under no-noise conditions (i.e., linearly separable data). We also extend our analysis to the noisy case and provide theoretical guarantees for our algorithm under the influence of noise in the task of binary and multi-class classification.

Related papers

• Robust optimization for adversarial learning with finite sample complexity guarantees [1.8434042562191815]
  In this paper we focus on linear and nonlinear classification problems and propose a novel adversarial training method for robust classifiers. We view robustness under a data driven lens, and derive finite sample complexity bounds for both linear and non-linear classifiers in binary and multi-class scenarios. Our algorithm minimizes a worst-case surrogate loss using Linear Programming (LP) and Second Order Cone Programming (SOCP) for linear and non-linear models.
  arXiv  Detail & Related papers  (2024-03-22T13:49:53Z)
• Understanding Uncertainty Sampling [7.32527270949303]
  Uncertainty sampling is a prevalent active learning algorithm that queries sequentially the annotations of data samples. We propose a notion of equivalent loss which depends on the used uncertainty measure and the original loss function. We provide the first generalization bound for uncertainty sampling algorithms under both stream-based and pool-based settings.
  arXiv  Detail & Related papers  (2023-07-06T01:57:37Z)
• Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise [62.997667081978825]
  In high-risk environments, deep learning models need to be able to judge their uncertainty and reject inputs when there is a significant chance of misclassification. We conduct a rigorous evaluation of the most commonly used uncertainty and robustness methods for the classification of Whole Slide Images. We observe that ensembles of methods generally lead to better uncertainty estimates as well as an increased robustness towards domain shifts and label noise.
  arXiv  Detail & Related papers  (2023-01-03T11:34:36Z)
• Improved Algorithms for Neural Active Learning [74.89097665112621]
  We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. We introduce two regret metrics by minimizing the population loss that are more suitable in active learning than the one used in state-of-the-art (SOTA) related work.
  arXiv  Detail & Related papers  (2022-10-02T05:03:38Z)
• Continual Learning For On-Device Environmental Sound Classification [63.81276321857279]
  We propose a simple and efficient continual learning method for on-device environmental sound classification. Our method selects the historical data for the training by measuring the per-sample classification uncertainty.
  arXiv  Detail & Related papers  (2022-07-15T12:13:04Z)
• BALanCe: Deep Bayesian Active Learning via Equivalence Class Annealing [7.9107076476763885]
  BALanCe is a deep active learning framework that mitigates the effect of uncertainty estimates. Batch-BALanCe is a generalization of the sequential algorithm to the batched setting. We show that Batch-BALanCe achieves state-of-the-art performance on several benchmark datasets for active learning.
  arXiv  Detail & Related papers  (2021-12-27T15:38:27Z)
• A Boosting Approach to Reinforcement Learning [59.46285581748018]
  We study efficient algorithms for reinforcement learning in decision processes whose complexity is independent of the number of states. We give an efficient algorithm that is capable of improving the accuracy of such weak learning methods.
  arXiv  Detail & Related papers  (2021-08-22T16:00:45Z)
• MCDAL: Maximum Classifier Discrepancy for Active Learning [74.73133545019877]
  Recent state-of-the-art active learning methods have mostly leveraged Generative Adversarial Networks (GAN) for sample acquisition. We propose in this paper a novel active learning framework that we call Maximum Discrepancy for Active Learning (MCDAL) In particular, we utilize two auxiliary classification layers that learn tighter decision boundaries by maximizing the discrepancies among them.
  arXiv  Detail & Related papers  (2021-07-23T06:57:08Z)
• A General Method for Robust Learning from Batches [56.59844655107251]
  We consider a general framework of robust learning from batches, and determine the limits of both classification and distribution estimation over arbitrary, including continuous, domains. We derive the first robust computationally-efficient learning algorithms for piecewise-interval classification, and for piecewise-polynomial, monotone, log-concave, and gaussian-mixture distribution estimation.
  arXiv  Detail & Related papers  (2020-02-25T18:53:25Z)
• On Last-Layer Algorithms for Classification: Decoupling Representation from Uncertainty Estimation [27.077741143188867]
  We propose a family of algorithms which split the classification task into two stages: representation learning and uncertainty estimation. We evaluate their performance in terms of emphselective classification (risk-coverage), and their ability to detect out-of-distribution samples.
  arXiv  Detail & Related papers  (2020-01-22T15:08:30Z)
• Noise-tolerant, Reliable Active Classification with Comparison Queries [25.725730509014355]
  We study the paradigm of active learning, in which algorithms with access to large pools of data may adaptively choose what samples to label. We provide the first time and query efficient algorithms for learning non-homogeneous linear separators robust to bounded (Massart) noise.
  arXiv  Detail & Related papers  (2020-01-15T19:00:00Z)

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.