mlsanityData to 7 Oct 2026

PAC Prediction Sets for Meta-Learning

arXiv 2207.02440 ↗First posted 6 Jul 2022cs.LG stat.MLcited by 16

Not on the map. Why?

Abstract (arXiv)

Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles. We study this problem in the context of meta learning, where the goal is to quickly adapt a predictor to new tasks. In particular, we propose a novel algorithm to construct PAC prediction sets, which capture uncertainty via sets of labels, that can be adapted to new tasks with only a few training examples. These prediction sets satisfy an extension of the typical PAC guarantee to the meta learning setting; in particular, the PAC guarantee holds with high probability over future tasks. We demonstrate the efficacy of our approach on four datasets across three application domains: mini-ImageNet and CIFAR10-C in the visual domain, FewRel in the language domain, and the CDC Heart Dataset in the medical domain. In particular, our prediction sets satisfy the PAC guarantee while having smaller size compared to other baselines that also satisfy this guarantee.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). Builds on 14 of its 27 references that are in the map. First posted on arXiv 6 Jul 2022.

Builds on

14 of 27 references.

References · 14

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2019Conformal Prediction Under Covariate Shiftcited by 511
  6. 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
  7. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  8. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  9. 2018FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluationcited by 254
  10. 2013Learning by Transductioncited by 120
  11. 2019PAC Confidence Sets for Deep Neural Networks via Calibrated Predictioncited by 59
  12. 2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
2 more
  1. 2021PAC Prediction Sets Under Covariate Shiftcited by 42
  2. 2018Distribution-Free Prediction Sets for Two-Layer Hierarchical Modelscited by 34

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 4; 2025: 6.

16 papers.

Sort:

  1. 2023PAC Prediction Sets Under Label Shiftcited by 19
  2. 2022Few-Shot Calibration of Set Predictors via Meta-Learned Cross-Validation-Based Conformal Predictioncited by 17
  3. 2023Selective Generation for Controllable Language Modelscited by 15
  4. 2024Semi-Supervised Risk Control via Prediction-Powered Inferencecited by 13
  5. 2025Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularizationcited by 11
  6. 2022Conformal Frequency Estimation using Discrete Sketched Data with Coverage for Distinct Queriescited by 10
  7. 2025The Geometries of Truth Are Orthogonal Across Taskscited by 9
  8. 2023SymmPI: Predictive Inference for Data with Group Symmetriescited by 8
  9. 2025Conformal Information Pursuit for Interactively Guiding Large Language Modelscited by 7
  10. 2024Uncertainty Quantification for Neurosymbolic Programs via Compositional Conformal Predictioncited by 4
  11. 2025Statistical Methods in Generative AIcited by 4
  12. 2022ACon2: Adaptive Conformal Consensus for Provable Blockchain Oraclescited by 2
4 more
  1. 2025Singleton-Optimized Conformal Predictioncited by 2
  2. 2024Conformal Predictions for Probabilistically Robust Scalable Machine Learning Classificationcited by 1
  3. 2025Optimizing In-Context Learning for Efficient Full Conformal Predictioncited by 1
  4. 2024Fundus Image-based Visual Acuity Assessment with PAC-Guaranteescited by 0