mlsanityData to 7 Oct 2026

Improved Algorithms for Neural Active Learning

arXiv 2210.00423 ↗First posted 2 Oct 2022cs.LG stat.MLcited by 11

Not on the map. Why?

Abstract (arXiv)

We improve the theoretical and empirical performance of neural-network(NN)-based active learning algorithms for the non-parametric streaming setting. In particular, 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. Then, the proposed algorithm leverages the powerful representation of NNs for both exploitation and exploration, has the query decision-maker tailored for k-class classification problems with the performance guarantee, utilizes the full feedback, and updates parameters in a more practical and efficient manner. These careful designs lead to an instance-dependent regret upper bound, roughly improving by a multiplicative factor O(log T) and removing the curse of input dimensionality. Furthermore, we show that the algorithm can achieve the same performance as the Bayes-optimal classifier in the long run under the hard-margin setting in classification problems. In the end, we use extensive experiments to evaluate the proposed algorithm and SOTA baselines, to show the improved empirical performance.

Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). Builds on 28 of its 58 references that are in the map. First posted on arXiv 2 Oct 2022.

Builds on

28 of 58 references.

References · 28

  1. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  2. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  3. 2018A Convergence Theory for Deep Learning via Over-Parameterizationcited by 784
  4. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  5. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 572
  6. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 572
  7. 2020A Survey of Deep Active Learningcited by 547
  8. 2019Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networkscited by 221
  9. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  10. 2020Neural Thompson Samplingcited by 127
  11. 2021Batch Active Learning at Scalecited by 127
  12. 2020Confidence-Aware Learning for Deep Neural Networkscited by 113
16 more
  1. 2021Gone Fishing: Neural Active Learning with Fisher Embeddingscited by 88
  2. 2020A Survey of Active Learning for Text Classification using Deep Neural Networkscited by 50
  3. 2021EE-Net: Exploitation-Exploration Neural Networks in Contextual Banditscited by 43
  4. 2016A Benchmark and Comparison of Active Learning for Logistic Regressioncited by 36
  5. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  6. 2020Efficient active learning of sparse halfspaces with arbitrary bounded noisecited by 29
  7. 2021Local Clustering in Contextual Multi-Armed Banditscited by 29
  8. 2021Neural Active Learning with Performance Guaranteescited by 22
  9. 2021Diversity Enhanced Active Learning with Strictly Proper Scoring Rulescited by 22
  10. 2021Multi-facet Contextual Bandits: A Neural Network Perspectivecited by 20
  11. 2020Generic Outlier Detection in Multi-Armed Banditcited by 14
  12. 2018Efficient active learning of sparse halfspacescited by 13
  13. 2017Adaptivity to Noise Parameters in Nonparametric Active Learningcited by 12
  14. 2018Uncertainty Sampling is Preconditioned Stochastic Gradient Descent on Zero-One Losscited by 10
  15. 2022Neural Bandit with Arm Group Graphcited by 8
  16. 2022Neural Collaborative Filtering Bandits via Meta Learningcited by 7

Built on by

Cited by year

Citing papers per year: 2023: 5; 2024: 4; 2025: 2.

11 papers.

  1. 2023Streaming Active Learning with Deep Neural Networkscited by 20
  2. 2025Adaptive Batch-Wise Sample Scheduling for Direct Preference Optimizationcited by 16
  3. 2024PageRank Bandits for Link Predictioncited by 14
  4. 2023Neural Contextual Bandits for Personalized Recommendationcited by 10
  5. 2024Neural Active Learning Beyond Banditscited by 10
  6. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
  7. 2024Meta Clustering of Neural Banditscited by 7
  8. 2023Active Cost-aware Labeling of Streaming Datacited by 2
  9. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 2
  10. 2024Neural Active Learning Meets the Partial Monitoring Frameworkcited by 1
  11. 2025Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticitycited by 1