---

Book

---

Theoretical foundations of conformal prediction.

Anastasios N. Angelopoulos, Rina Foygel Barber, and Stephen Bates.
See arXiv:2411.11824 for a preliminary version of Parts I, II, III of the book.

This material will be published by Cambridge University Press as Theoretical Foundations of Conformal Prediction by Anastasios N. Angelopoulos, Rina Foygel Barber and Stephen Bates. This prepublication version is free to view/download for personal use only. Not for redistribution/resale/use in derivative works. Copyright Anastasios N. Angelopoulos, Rina Foygel Barber and Stephen Bates, 2024.

---

Publications & preprints (organized by year)

---

2024

• Conformal prediction after efficiency-oriented model selection.
  Ruiting Liang, Wanrong Zhu, and Rina Foygel Barber. arXiv:2408.07066

• Distributionally robust risk evaluation with an isotonic constraint. (Code.)
  Yu Gui, Rina Foygel Barber, and Cong Ma. arXiv:2407.06867

• Boosted Conformal Prediction Intervals. (Code.)
  Ran Xie, Rina Foygel Barber, and Emmanuel Candès. To appear in Advances in Neural Information Processing Systems 37 (NeurIPS 2024). arXiv:2406.07449

• Is algorithmic stability testable? A unified framework under computational constraints.
  Yuetian Luo and Rina Foygel Barber. arXiv:2405.15107

• Building a stable classifier with the inflated argmax. (Code.)
  Jake A. Soloff, Rina Foygel Barber, and Rebecca Willett. To appear in Advances in Neural Information Processing Systems 37 (NeurIPS 2024). arXiv:2405.14064

• Stability via resampling: statistical problems beyond the real line. (Code.)
  Jake A. Soloff, Rina Foygel Barber, and Rebecca Willett. arXiv:2405.09511

• The mosaic permutation test: an exact and nonparametric goodness-of-fit test for factor models. (Code.)
  Asher Spector, Rina Foygel Barber, Trevor Hastie, Ronald N. Kahn, and Emmanuel Candès. arXiv:2404.15017

• Hoeffding and Bernstein inequalities for weighted sums of exchangeable random variables.
  Rina Foygel Barber. Electronic Communications in Probability 29: 1-13. arXiv:2404.06457

• The Limits of Assumption-free Tests for Algorithm Performance.
  Yuetian Luo and Rina Foygel Barber. arXiv:2402.07388

• Online conformal prediction with decaying step sizes. (Code.)
  Anastasios N. Angelopoulos, Rina Foygel Barber, and Stephen Bates. 41st International Conference on Machine Learning (ICML 2024). arXiv:2402.01139

• Group-Weighted Conformal Prediction. (Code.)
  Aabesh Bhattacharyya and Rina Foygel Barber. arXiv:2401.17452

2023

• Algorithmic stability implies training-conditional coverage for distribution-free prediction methods. (Code.)
  Ruiting Liang and Rina Foygel Barber. arXiv:2311.04295

• Conformal prediction with local weights: randomization enables robust guarantees. (Code.)
  Rohan Hore and Rina Foygel Barber. To appear in Journal of the Royal Statistical Society - Series B. arXiv:2310.07850

• Approximate co-sufficient sampling with regularization. (Code.)
  Wanrong Zhu and Rina Foygel Barber. arXiv:2309.08063

• Constrained one-step material decomposition reconstruction of head CT data from a silicon photon-counting prototype.
  Taly Gilat Schmidt, Emil Y. Sidky, Xiaochuan Pan, Rina Foygel Barber, Fredrik Grönberg, Martin Sjölin, and Mats Danielsson. Medical Physics 50: 6008-6021.

• Integrating Uncertainty Awareness into Conformalized Quantile Regression. (Code.)
  Raphael Rossellini, Rina Foygel Barber, and Rebecca Willett. 27th International Conference on Artificial Intelligence and Statistics (AISTATS 2024). arXiv:2306.08693

• Distribution-free inference with hierarchical data.
  Yonghoon Lee, Rina Foygel Barber, and Rebecca Willett. arXiv:2306.06342

• Conformalized matrix completion. (Code.)
  Yu Gui, Rina Foygel Barber, and Cong Ma. Advances in Neural Information Processing Systems 36 (NeurIPS 2023). arXiv:2305.10637

• Pharmacokinetic Analysis of Enhancement-Constrained Acceleration (ECA) reconstruction-based high temporal resolution breast DCE-MRI.
  Zhen Ren, Ty O. Easley, Federico D. Pineda, Xiaodong Guo, Rina Foygel Barber, and Gregory S. Karczmar. PLoS ONE 18(6): e0286123.

• De Finetti’s Theorem and Related Results for Infinite Weighted Exchangeable Sequences. (Slides.)
  Rina Foygel Barber, Emmanuel J. Candès, Aaditya Ramdas, and Ryan Tibshirani. Bernoulli 30(4): 3004-3028. arxiv:2304.03927

• Simultaneous activity and attenuation estimation in TOF-PET with TV-constrained nonconvex optimization. (Code.)
  Zhimei Ren, Emil Y. Sidky, Rina Foygel Barber, Chien-Min Kao, and Xiaochuan Pan. IEEE Transactions on Medical Imaging 43(6): 2347-2357. arXiv:2303.17042

• Iterative Approximate Cross-Validation. (Code.)
  Yuetian Luo, Zhimei Ren, and Rina Foygel Barber. 40th International Conference on Machine Learning (ICML 2023). arxiv:2303.02732

• Selective inference for clustering with unknown variance. (Code.)
  Young-Joo Yun and Rina Foygel Barber. Electronic Journal of Statistics 17(2): 1923-1946. arxiv:2301.12999

• Bagging Provides Assumption-free Stability. (Code; Slides.)
  Jake A. Soloff, Rina Foygel Barber, and Rebecca Willett. arxiv:2301.12600

2022

• Conformalized survival analysis with adaptive cutoffs. (Code.)
  Yu Gui, Rohan Hore, Zhimei Ren, and Rina Foygel Barber. Biometrika 111(2): 459-477. arxiv:2211.01227

• Derandomized Knockoffs: Leveraging E-values for False Discovery Rate Control. (Code.)
  Zhimei Ren and Rina Foygel Barber. Journal of the Royal Statistical Society - Series B 86(1): 122-154. arXiv:2205.15461

• Training-conditional coverage for distribution-free predictive inference. (Code.)
  Michael Bian and Rina Foygel Barber. Electronic Journal of Statistics 17(2): 2044-2066. arXiv:2205.03647

• Permutation tests using arbitrary permutation distributions.
  Aaditya Ramdas, Rina Foygel Barber, Emmanuel J. Candès, and Ryan Tibshirani. Sankhya A 85: 1156-1177. arXiv:2204.13581

• Conformal prediction beyond exchangeability. (Code; Slides.)
  Rina Foygel Barber, Emmanuel J. Candès, Aaditya Ramdas, and Ryan Tibshirani. Annals of Statistics 51(2): 816-845. arXiv:2202.13415

• Addressing CT metal artifacts using photon-counting detectors and one-step spectral CT image reconstruction.
  Taly Gilat Schmidt, Barbara A. Sammut, Rina Foygel Barber, Xiaochuan Pan, and Emil Y. Sidky. Medical Physics 49(5):3021-3040.

• Enhancement-Constrained Acceleration: A Robust Reconstruction Framework in Breast DCE-MRI. (Code.)
  Ty Easley, Zhen Ren, Byol Kim, Gregory Karczmar, Rina Foygel Barber, and Federico D Pineda. PLoS ONE 16(10): e0258621.

• Half-trek criterion for identifiability of latent variable models.
  Rina Foygel Barber, Mathias Drton, Nils Sturma, and Luca Weihs. Annals of Statistics 50(6): 3174-3196. arXiv:2201.04457

2021

• Black-box tests for algorithmic stability. (Slides.)
  Byol Kim and Rina Foygel Barber. Information and Inference 12(4): 2690-2719. arXiv:2111.15546

• Binary classification with corrupted labels.
  Yonghoon Lee and Rina Foygel Barber. Electronic Journal of Statistics 16(1): 1367-1392. arXiv:2106.09136

• Distribution-free inference for regression: discrete, continuous, and in between. (Slides.)
  Yonghoon Lee and Rina Foygel Barber. Advances in Neural Information Processing Systems 34 (NeurIPS 2021). arXiv:2105.14075

• Convergence guarantee for the sparse monotone single index model.
  Ran Dai, Hyebin Song, Rina Foygel Barber, and Garvesh Raskutti. Electronic Journal of Statistics 16(2): 4449-4496. arXiv:2105.07587

2020

• A Power Analysis for Model-X Knockoffs with Lp-Regularized Statistics.
  Asaf Weinstein, Weijie J. Su, Malgorzata Bogdan, Rina Foygel Barber, and Emmanuel J. Candès. Annals of Statistics 51(3): 1005-1029. arXiv:2007.15346

• Testing goodness-of-fit and conditional independence with approximate co-sufficient sampling. (Code; Slides.)
  Rina Foygel Barber and Lucas Janson. Annals of Statistics 50(5): 2514-2544. arXiv:2007.09851

• Convergence for nonconvex ADMM, with applications to CT imaging. (Code.)
  Rina Foygel Barber and Emil Y. Sidky. Journal of Machine Learning Research 25(38): 1-46. arXiv:2006.07278

• Is distribution-free inference possible for binary regression? (Slides.)
  Rina Foygel Barber. Electronic Journal of Statistics 14(2): 3487-3524. arXiv:2004.09477

• Predictive Inference Is Free with the Jackknife+-after-Bootstrap. (Code.)
  Byol Kim, Chen Xu, and Rina Foygel Barber. Advances in Neural Information Processing Systems 33 (NeurIPS 2020). arXiv:2002.09025

• Spectral CT metal artifact reduction using weighted masking and a one step direct inversion reconstruction algorithm.
  Taly Gilat Schmidt, Rina Foygel Barber, and Emil Y. Sidky. Proceedings of the SPIE Conference on Medical Imaging 2020: Physics of Medical Imaging.

• Local continuity of log-concave projection, with applications to estimation under model misspecification.
  Rina Foygel Barber and Richard Samworth. Bernoulli 27(4): 2437-2472. arXiv:2002.06117

• Fast and Flexible Estimation of Effective Migration Surfaces.
  Joseph H. Marcus, Wooseok Ha, Rina Foygel Barber, and John Novembre. eLife, 10, e61927. bioRXiv:2020.08.07.242214

2019

• Convex and Non-convex Approaches for Statistical Inference with Noisy Labels.
  Hyebin Song, Ran Dai, Garvesh Raskutti, and Rina Foygel Barber. Journal of Machine Learning Research 21(168):1-58. arXiv:1910.02348

• With Malice Towards None: Assessing Uncertainty via Equalized Coverage. (Code here and here.)
  Yaniv Romano, Rina Foygel Barber, Chiara Sabatti, and Emmanuel J. Candès. Harvard Data Science Review 2(2). arXiv:1908.05428

• The bias of isotonic regression. (Code.)
  Ran Dai, Hyebin Song, Rina Foygel Barber, and Garvesh Raskutti. Electronic Journal of Statistics 14(1): 801-834. arXiv:1908.04462

• Predictive inference with the jackknife+. (Code.)
  Rina Foygel Barber, Emmanuel J. Candès, Aaditya Ramdas, and Ryan Tibshirani. Annals of Statistics 49(1): 486-507. arXiv:1905.02928

• Conformal prediction under covariate shift. (Code.)
  Ryan Tibshirani, Rina Foygel Barber, Emmanuel J. Candès, and Aaditya Ramdas. Advances in Neural Information Processing Systems 32 (NeurIPS 2019). arXiv:1904.06019

• The limits of distribution-free conditional predictive inference.
  Rina Foygel Barber, Emmanuel J. Candès, Aaditya Ramdas, and Ryan Tibshirani. Information and Inference 10(2): 455-482. arXiv:1903.04684

2018

• On the construction of knockoffs in case-control studies.
  Rina Foygel Barber and Emmanuel J. Candès. STAT 8(1). arXiv:1812.11433

• An equivalence between critical points for rank constraints versus low-rank factorizations.
  Wooseok Ha, Haoyang Liu, and Rina Foygel Barber. SIAM Journal on Optimization: 30(4) 2927-2955. arXiv:1812.00404

• Alternating minimization based framework for simultaneous spectral calibration and image reconstruction in spectral CT.
  Wooseok Ha, Emil Y Sidky, Rina Foygel Barber, Taly Gilat Schmidt, and Xiaochuan Pan. 2018 IEEE Nuclear Science Symposium and Medical Imaging Conference.

• The conditional permutation test for independence while controlling for confounders. (Code.)
  Thomas B. Berrett, Yi Wang, Rina Foygel Barber, and Richard J. Samworth. Journal of the Royal Statistical Society - Series B 82(1) 175-197. arXiv:1807.05405

• Prediction rule reshaping.
  Matt Bonakdarpour, Sabyasachi Chatterjee, Rina Foygel Barber, and John Lafferty. 35th International Conference on Machine Learning (ICML 2018). arXiv:1805.06439

• Estimating the spectrum in computed tomography via Kullback-Leibler divergence constrained optimization.
  Wooseok Ha, Emil Y. Sidky, Rina Foygel Barber, Taly Gilat Schmidt, and Xiaochuan Pan. Medical Physics 46(1): 81-92. arXiv:1805.00162

• Between hard and soft thresholding: optimal iterative thresholding algorithms.
  Haoyang Liu and Rina Foygel Barber. Information and Inference 9(4): 899-933. arXiv:1804.08841

• Three material decomposition for spectral computed tomography enabled by block-diagonal step-preconditioning.
  Emil Y. Sidky, Rina Foygel Barber, Taly Gilat Schmidt, and Xiaochuan Pan. arXiv:1801.06263

• Robust inference with knockoffs.
  Rina Foygel Barber, Emmanuel J. Candès, and Richard J. Samworth. Annals of Statistics 48(3): 1409-1431. arXiv:1801.03896

2017

• A power and prediction analysis for knockoffs with Lasso statistics.
  Asaf Weinstein, Rina Foygel Barber, and Emmanuel J. Candès. arXiv:1712.06465

• Discretized conformal prediction for efficient distribution-free inference. (Code.)
  Wenyu Chen, Kelli-Jean Chun, and Rina Foygel Barber. STAT 7(1). arXiv:1709.06233

• A Spectral CT method to directly estimate basis material maps from experimental photon-counting data.
  Taly Gilat Schmidt, Rina Foygel Barber, and Emil Y. Sidky. IEEE Transactions on Medical Imaging 36(9):1808-1819.

• X-ray spectral calibration from transmission measurements using Gaussian blur model.
  Wooseok Ha, Emil Y. Sidky, and Rina Foygel Barber. Proceedings of the SPIE Conference on Medical Imaging 2017: Physics of Medical Imaging.

• Spectral CT metal artifact reduction with an optimization-based reconstruction algorithm.
  Taly Gilat Schmidt, Rina Foygel Barber, and Emil Y. Sidky. Proceedings of the SPIE Conference on Medical Imaging 2017: Physics of Medical Imaging.

• Alternating minimization and alternating descent over nonconvex sets. (Code.)
  Wooseok Ha and Rina Foygel Barber. arXiv:1709.04451

• Contraction and uniform convergence of isotonic regression. (Code.)
  Fan Yang and Rina Foygel Barber. Electronic Journal of Statistics 13(1): 646-677. arXiv:1706.01852

• Gradient descent with nonconvex constraints: local concavity determines convergence. (Code.)
  Rina Foygel Barber and Wooseok Ha. Information and Inference 7(4): 755-806. arXiv:1703.07755

• A unified treatment of multiple testing with prior knowledge. (Code.)
  Aaditya Ramdas, Rina Foygel Barber, Martin J. Wainwright, and Michael I. Jordan. Annals of Statistics 47(5): 2790-2821. arXiv:1703.06222

2016

• Trimmed conformal prediction for high-dimensional models.
  Wenyu Chen, Zhaokai Wang, Wooseok Ha, and Rina Foygel Barber. arXiv:1611.09933

• The Function-on-scalar LASSO with applications to longitudinal GWAS.
  Rina Foygel Barber, Matthew Reimherr, and Thomas Schill. Electronic Journal of Statistics 11(1): 1351-1389. arXiv:1610.07403

• Selective inference for group-sparse linear models. (Code.)
  Fan Yang, Rina Foygel Barber, Prateek Jain, and John Lafferty. Advances in Neural Information Processing Systems 29 (NeurIPS 2016). arXiv:1607.08211

• Multiple testing with the structure adaptive Benjamini-Hochberg algorithm. (Code.)
  Ang Li and Rina Foygel Barber. Journal of the Royal Statistical Society - Series B 81(1): 45-74. arXiv:1606.07926

• The knockoff filter for FDR control in group-sparse and multitask regression.
  Ran Dai and Rina Foygel Barber. 33rd International Conference on Machine Learning (ICML 2016). arXiv:1602.03589

• A knockoff filter for high-dimensional selective inference.
  Rina Foygel Barber and Emmanuel J. Candès. Annals of Statistics 47(5): 2504-2537. arXiv:1602.03574

2015

• The p-filter: multilayer FDR control for grouped hypotheses. (Code.)
  Rina Foygel Barber and Aaditya Ramdas. Journal of the Royal Statistical Society - Series B 79(4): 1247-1268. arXiv:1512.03397

• An algorithm for constrained one-step inversion of spectral CT data.
  Rina Foygel Barber, Emil Y. Sidky, Taly Gilat Schmidt, and Xiaochuan Pan. Physics in Medicine and Biology 61: 3784-3818. arXiv:1511.03384

• MOCCA: mirrored convex/concave optimization for nonconvex composite functions. (Code; Slides.)
  Rina Foygel Barber and Emil Y. Sidky. Journal of Machine Learning Research 17: 1-51. arXiv:1510.08842

• Accumulation tests for FDR control in ordered hypothesis testing. (Code.)
  Ang Li and Rina Foygel Barber. Journal of the American Statistical Association 112(518): 837-849. arXiv:1505.07352

• EigenPrism: inference for high-dimensional signal-to-noise ratios.
  Lucas Janson, Rina Foygel Barber, and Emmanuel J. Candès. Journal of the Royal Statistical Society - Series B 79(4): 1037-1065. arXiv:1505.02097

• Laplace approximation in high-dimensional Bayesian regression.
  Rina Foygel Barber, Mathias Drton, and Kean Ming Tan. Springer series Abel Symposium vol 11 (Statistical Analysis for High Dimensional Data): 15-36. arXiv:1503.08337

• Robust PCA with compressed data.
  Wooseok Ha and Rina Foygel Barber. Advances in Neural Information Processing Systems 28 (NeurIPS 2015).

• ROCKET: robust confidence intervals via Kendall’s Tau for transelliptical graphical models. (Code.)
  Rina Foygel Barber and Mladen Kolar. Annals of Statistics 46(6B): 3422-3450. arXiv:1502.07641

• Inferring skeletal production from time-averaged assemblages: skeletal loss pulls the timing of production pulses towards the modern period.
  Adam Tomasovych, Susan M. Kidwell, and Rina Foygel Barber. Paleobiology 42(1): 54-76.

2014

• Privacy and statistical risk: Formalisms and minimax bounds.
  Rina Foygel Barber and John Duchi. arXiv:1412.4451
  Shorter conference version: Privacy: a few definitional aspects and consequences for minimax mean-squared error. 53rd IEEE Conference on Decision and Control (CDC 2014).

• The log-shift penalty for adaptive estimation of multiple Gaussian graphical models.
  Yuancheng Zhu and Rina Foygel Barber. 18th International Conference on Artificial Intelligence and Statistics (AISTATS 2015). arXiv:1406.1812

• Controlling the false discovery rate via knockoffs. (Code; Slides.)
  Rina Foygel Barber and Emmanuel J. Candès. Annals of Statistics 43(5):2055-2085. arXiv:1404.5609

• High-dimensional Ising model selection with Bayesian information criteria.
  Rina Foygel Barber and Mathias Drton. Electronic Journal of Statistics 9:567-607. arXiv:1403.3374

• Long-term accumulation of carbonate shells reflects a 100-fold drop in loss rate.
  Adam Tomasovych, Susan M. Kidwell, Rina Foygel Barber, and Darrell S. Kaufman. Geology 42(9):819-822.

2013

• Corrupted sensing: novel guarantees for separating structured signals.
  Rina Foygel and Lester Mackey. IEEE Transactions on Information Theory 60(2): 1223-1247. arXiv:1305.2524

2012

• Nonparametric reduced rank regression.
  Rina Foygel, Michael Horrell, Mathias Drton, and John Lafferty. Advances in Neural Information Processing Systems 25 (NeurIPS 2012). arXiv:1301.1919

• Matrix reconstruction with the local max norm.
  Rina Foygel, Nathan Srebro, and Ruslan Salakhutdinov. Advances in Neural Information Processing Systems 25 (NeurIPS 2012). arXiv:1210.5196

• Sparse Prediction with the k-Support Norm.
  Andreas Argyriou, Rina Foygel, and Nathan Srebro. Advances in Neural Information Processing Systems 25 (NeurIPS 2012). arXiv:1204.5043

2011

• Bayesian model choice and information criteria in sparse generalized linear models.
  Rina Foygel and Mathias Drton. arXiv:1112.5635

• Fast-rate and optimistic-rate error bounds for L1-regularized regression.
  Rina Foygel and Nathan Srebro. arXiv:1108.0373

• Half-trek criterion for generic identifiability of linear structural equation models. (Code.)
  Rina Foygel, Jan Draisma, and Mathias Drton. Annals of Statistics 40(3): 1682-1713. arXiv:1107.5552

• Learning with the weighted trace-norm under arbitrary sampling distributions.
  Rina Foygel, Ruslan Salakhutdinov, Ohad Shamir, and Nathan Srebro. Advances in Neural Information Processing Systems 24 (NeurIPS 2011). arXiv:1106.4251

• Concentration-based guarantees for low-rank matrix reconstruction.
  Rina Foygel and Nathan Srebro. 24th Annual Conference on Learning Theory (COLT 2011). arXiv:1102.3923

2010

• Extended Bayesian information criteria for Gaussian graphical models.
  Rina Foygel and Mathias Drton. Advances in Neural Information Processing Systems 23 (NeurIPS 2010). arXiv:1011.6640

• Exact block-wise optimization in group lasso for linear regression.
  Rina Foygel and Mathias Drton. arXiv:1010.3320

• Global identifiability of linear structural equation models. (Code.)
  Mathias Drton, Rina Foygel, and Seth Sullivant. Annals of Statistics 39(2):865-886. arXiv:1003.1146