mlsanityData to 7 Oct 2026

TorchCP: A Python Library for Conformal Prediction

arXiv 2402.12683 ↗First posted 20 Feb 2024cs.LG cs.CV math.STcited by 9

Not on the map. Why?

Abstract (arXiv)

Conformal prediction (CP) is a powerful statistical framework that generates prediction intervals or sets with guaranteed coverage probability. While CP algorithms have evolved beyond traditional classifiers and regressors to sophisticated deep learning models like deep neural networks (DNNs), graph neural networks (GNNs), and large language models (LLMs), existing CP libraries often lack the model support and scalability for large-scale deep learning (DL) scenarios. This paper introduces TorchCP, a PyTorch-native library designed to integrate state-of-the-art CP algorithms into DL techniques, including DNN-based classifiers/regressors, GNNs, and LLMs. Released under the LGPL-3.0 license, TorchCP comprises about 16k lines of code, validated with 100% unit test coverage and detailed documentation. Notably, TorchCP enables CP-specific training algorithms, online prediction, and GPU-accelerated batch processing, achieving up to 90% reduction in inference time on large datasets. With its low-coupling design, comprehensive suite of advanced methods, and full GPU scalability, TorchCP empowers researchers and practitioners to enhance uncertainty quantification across cutting-edge applications.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 29 of its 61 references that are in the map. First posted on arXiv 20 Feb 2024.

Builds on

29 of 61 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2017TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehensioncited by 2,895
  4. 2016Distribution-Free Predictive Inference For Regressioncited by 657
  5. 2019Conformalized Quantile Regressioncited by 620
  6. 2019Conformal Prediction Under Covariate Shiftcited by 511
  7. 2020Classification with Valid and Adaptive Coveragecited by 390
  8. 2020Uncertainty Sets for Image Classifiers using Conformal Predictioncited by 365
  9. 2021Adaptive Conformal Inference Under Distribution Shiftcited by 360
  10. 2022Conformal prediction beyond exchangeabilitycited by 348
  11. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  12. 2016Least Ambiguous Set-Valued Classifiers with Bounded Error Levelscited by 270
17 more
  1. 2023Conformal Language Modelingcited by 163
  2. 2022Adaptive Conformal Predictions for Time Seriescited by 155
  3. 2023Class-Conditional Conformal Prediction with Many Classescited by 109
  4. 2021Learning Optimal Conformal Classifierscited by 108
  5. 2023Uncertainty Quantification over Graph with Conformalized Graph Neural Networkscited by 79
  6. 2019A comparison of some conformal quantile regression methodscited by 76
  7. 2022Training Uncertainty-Aware Classifiers with Conformalized Deep Learningcited by 62
  8. 2014Regression Conformal Prediction with Nearest Neighbourscited by 59
  9. 2019Adaptive, Distribution-Free Prediction Intervals for Deep Networkscited by 56
  10. 2023Conformal Prediction for Deep Classifier via Label Rankingcited by 52
  11. 2022Distribution Free Prediction Sets for Node Classificationcited by 28
  12. 2021Optimized conformal classification using gradient descent approximationcited by 27
  13. 2023Fortuna: A Library for Uncertainty Quantification in Deep Learningcited by 14
  14. 2023Guaranteed Coverage Prediction Intervals with Gaussian Process Regressioncited by 12
  15. 2024Does confidence calibration improve conformal prediction?cited by 12
  16. 2023Reliable Prediction Intervals with Regression Neural Networkscited by 11
  17. 2023Empirically Validating Conformal Prediction on Modern Vision Architectures Under Distribution Shift and Long-tailed Datacited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 4; 2026: 3.

9 papers.

  1. 2024Conformal Prediction: A Data Perspectivecited by 25
  2. 2024Conformal Thresholded Intervals for Efficient Regressioncited by 11
  3. 2025Torch-Uncertainty: A Deep Learning Framework for Uncertainty Quantificationcited by 4
  4. 2025Semi-Supervised Conformal Prediction With Unlabeled Nonconformity Scorecited by 1
  5. 2025Provable Training Data Identification for Large Language Modelscited by 1
  6. 2025Quantifying and Improving Adaptivity in Conformal Prediction through Input Transformationscited by 0
  7. 2026Softmax is not Enough (for Adaptive Conformal Classification)cited by 0
  8. 2026Cluster Frequency Conformal Prediction for Local Coveragecited by 0
  9. 2026tsbootstrap: Distribution-Free Uncertainty Quantification and Conformal Prediction for Time Seriescited by 0