mlsanityData to 7 Oct 2026

Neural Active Learning with Performance Guarantees

arXiv 2106.03243 ↗First posted 6 Jun 2021cs.LGcited by 22

Not on the map. Why?

Abstract (arXiv)

We investigate the problem of active learning in the streaming setting in non-parametric regimes, where the labels are stochastically generated from a class of functions on which we make no assumptions whatsoever. We rely on recently proposed Neural Tangent Kernel (NTK) approximation tools to construct a suitable neural embedding that determines the feature space the algorithm operates on and the learned model computed atop. Since the shape of the label requesting threshold is tightly related to the complexity of the function to be learned, which is a-priori unknown, we also derive a version of the algorithm which is agnostic to any prior knowledge. This algorithm relies on a regret balancing scheme to solve the resulting online model selection problem, and is computationally efficient. We prove joint guarantees on the cumulative regret and number of requested labels which depend on the complexity of the labeling function at hand. In the linear case, these guarantees recover known minimax results of the generalization error as a function of the label complexity in a standard statistical learning setting.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 23 of its 46 references that are in the map. First posted on arXiv 6 Jun 2021.

Builds on

23 of 46 references.

References · 23

  1. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  2. 2019Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Boundscited by 602
  3. 2018Gradient Descent Finds Global Minima of Deep Neural Networkscited by 572
  4. 2019On Exact Computation with an Infinitely Wide Neural Netcited by 572
  5. 2019BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learningcited by 428
  6. 2017On Kernelized Multi-armed Banditscited by 348
  7. 2019Generalization Bounds of Stochastic Gradient Descent for Wide and Deep Neural Networkscited by 221
  8. 2018Time-uniform, nonparametric, nonasymptotic confidence sequencescited by 220
  9. 2013Finite-Time Analysis of Kernelised Contextual Banditscited by 177
  10. 2019On the Inductive Bias of Neural Tangent Kernelscited by 177
  11. 2019Towards Understanding the Spectral Bias of Deep Learningcited by 173
  12. 2020Neural Thompson Samplingcited by 127
11 more
  1. 2019Diverse mini-batch Active Learningcited by 88
  2. 2020Model Selection in Contextual Stochastic Bandit Problemscited by 71
  3. 2014Rates of Convergence for Nearest Neighbor Classificationcited by 45
  4. 2020Regret Bound Balancing and Elimination for Model Selection in Bandits and RLcited by 45
  5. 2017Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minimacited by 40
  6. 2021On the Approximation Power of Two-Layer Networks of Random ReLUscited by 29
  7. 2018Deep Ensemble Bayesian Active Learning : Addressing the Mode Collapse issue in Monte Carlo dropout via Ensemblescited by 20
  8. 2017Adaptivity to Noise Parameters in Nonparametric Active Learningcited by 12
  9. 2019MaxiMin Active Learning in Overparameterized Model Classes}cited by 10
  10. 2016Active Nearest-Neighbor Learning in Metric Spacescited by 9
  11. 2021Nonparametric adaptive active learning under local smoothness conditioncited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 5; 2024: 6; 2025: 2; 2026: 1.

22 papers.

Sort:

By area:

  1. 2022A Framework and Benchmark for Deep Batch Active Learning for Regressioncited by 47
  2. 2021Deep Active Learning by Leveraging Training Dynamicscited by 32
  3. 2024PINNACLE: PINN Adaptive ColLocation and Experimental points selectioncited by 31
  4. 2022Sample-Then-Optimize Batch Neural Thompson Samplingcited by 25
  5. 2022Fast Rates in Pool-Based Batch Active Learningcited by 15
  6. 2024PageRank Bandits for Link Predictioncited by 14
  7. 2022Active Learning with Neural Networks: Insights from Nonparametric Statisticscited by 13
  8. 2022Norm-Agnostic Linear Banditscited by 12
  9. 2022Improved Algorithms for Neural Active Learningcited by 11
  10. 2024Neural Active Learning Beyond Banditscited by 10
  11. 2026Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewardscited by 10
  12. 2023Neural Exploitation and Exploration of Contextual Banditscited by 7
10 more
  1. 2024Meta Clustering of Neural Banditscited by 7
  2. 2021Active Learning for Deep Neural Networks on Edge Devicescited by 6
  3. 2023Training-Free Neural Active Learning with Initialization-Robustness Guaranteescited by 5
  4. 2024Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samplescited by 5
  5. 2023Active Cost-aware Labeling of Streaming Datacited by 2
  6. 2023Few Clicks Suffice: Active Test-Time Adaptation for Semantic Segmentationcited by 2
  7. 2023Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approachcited by 1
  8. 2024Neural Active Learning Meets the Partial Monitoring Frameworkcited by 1
  9. 2025Empirical Bound Information-Directed Sampling for Norm-Agnostic Banditscited by 0
  10. 2025Constrained Online Decision-Making: A Unified Frameworkcited by 0