mlsanityData to 13 Oct 2026

Transductive Active Learning: Theory and Applications

arXiv 2402.15898 ↗First posted 13 Feb 2024cs.LG cs.AIcited by 22

Not on the map. Why?

Abstract (arXiv)

We study a generalization of classical active learning to real-world settings with concrete prediction targets where sampling is restricted to an accessible region of the domain, while prediction targets may lie outside this region. We analyze a family of decision rules that sample adaptively to minimize uncertainty about prediction targets. We are the first to show, under general regularity assumptions, that such decision rules converge uniformly to the smallest possible uncertainty obtainable from the accessible data. We demonstrate their strong sample efficiency in two key applications: active fine-tuning of large neural networks and safe Bayesian optimization, where they achieve state-of-the-art performance.

Key facts. Cited by 22 papers in the map (data through 13 Oct 2026). First posted on arXiv 13 Feb 2024.

Builds on

0 of 0 references.

No references here yet.

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2024: 2; 2025: 13; 2026: 7.

22 papers.

Sort:

By area:

  1. 2024Post-hoc Probabilistic Vision-Language Modelscited by 13
  2. 2025DISCOVER: Automated Curricula for Sparse-Reward Reinforcement Learningcited by 12
  3. 2025Local Mixtures of Experts: Essentially Free Test-Time Training via Model Mergingcited by 9
  4. 2025Learning on the Job: Test-Time Curricula for Targeted Reinforcement Learningcited by 9
  5. 2024Active Fine-Tuning of Multi-Task Policiescited by 8
  6. 2025Test-time Offline Reinforcement Learning on Goal-related Experiencecited by 8
  7. 2025Epistemically-guided forward-backward explorationcited by 6
  8. 2025Specialization after Generalization: Towards Understanding Test-Time Training in Foundation Modelscited by 5
  9. 2025LITE: Efficiently Estimating Gaussian Probability of Maximalitycited by 3
  10. 2025Distributionally Robust Active Learning for Gaussian Process Regressioncited by 3
  11. 2025Causal-EPIG: A Prediction-Oriented Active Learning Framework for CATE Estimationcited by 2
  12. 2026Loss-Driven Bayesian Active Learningcited by 2
10 more
  1. 2025ActiveCQ: Active Estimation of Causal Quantitiescited by 1
  2. 2026Observationally Informed Adaptive Causal Experimental Designcited by 1
  3. 2025Simulation Priors for Data-Efficient Deep Learningcited by 0
  4. 2025Boosting Active Learning with Knowledge Transfercited by 0
  5. 2025Calibrated Uncertainty Sampling for Active Learningcited by 0
  6. 2026Active Learning for Gaussian Process Regression Under Self-Induced Boltzmann Weightscited by 0
  7. 2026Sampling-Based Safe Reinforcement Learningcited by 0
  8. 2026Joint Model and Data Sparsification via the Marginal Likelihoodcited by 0
  9. 2026Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolationcited by 0
  10. 2026ShaplEIG: Bayesian Experimental Design for Shapley Value Estimationcited by 0