PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction

• URL: http://arxiv.org/abs/2312.04658v1
• Date: Thu, 7 Dec 2023 19:40:44 GMT
• Title: PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction
• Authors: Apoorva Sharma, Sushant Veer, Asher Hancock, Heng Yang, Marco Pavone, Anirudha Majumdar
• Abstract summary: We use PAC-Bayes theory to obtain generalization bounds on the coverage and the efficiency of set-valued predictors. We leverage these theoretical results to provide a practical algorithm for using calibration data to fine-tune the parameters of a model and score function. We evaluate the approach on regression and classification tasks, and outperform baselines calibrated using a Hoeffding bound-based PAC guarantee on ICP.
• Score: 27.434939269672288
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Inductive Conformal Prediction (ICP) provides a practical and effective approach for equipping deep learning models with uncertainty estimates in the form of set-valued predictions which are guaranteed to contain the ground truth with high probability. Despite the appeal of this coverage guarantee, these sets may not be efficient: the size and contents of the prediction sets are not directly controlled, and instead depend on the underlying model and choice of score function. To remedy this, recent work has proposed learning model and score function parameters using data to directly optimize the efficiency of the ICP prediction sets. While appealing, the generalization theory for such an approach is lacking: direct optimization of empirical efficiency may yield prediction sets that are either no longer efficient on test data, or no longer obtain the required coverage on test data. In this work, we use PAC-Bayes theory to obtain generalization bounds on both the coverage and the efficiency of set-valued predictors which can be directly optimized to maximize efficiency while satisfying a desired test coverage. In contrast to prior work, our framework allows us to utilize the entire calibration dataset to learn the parameters of the model and score function, instead of requiring a separate hold-out set for obtaining test-time coverage guarantees. We leverage these theoretical results to provide a practical algorithm for using calibration data to simultaneously fine-tune the parameters of a model and score function while guaranteeing test-time coverage and efficiency of the resulting prediction sets. We evaluate the approach on regression and classification tasks, and outperform baselines calibrated using a Hoeffding bound-based PAC guarantee on ICP, especially in the low-data regime.

Related papers

• Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning [53.42244686183879]
  Conformal prediction provides model-agnostic and distribution-free uncertainty quantification. Yet, conformal prediction is not reliable under poisoning attacks where adversaries manipulate both training and calibration data. We propose reliable prediction sets (RPS): the first efficient method for constructing conformal prediction sets with provable reliability guarantees under poisoning.
  arXiv  Detail & Related papers  (2024-10-13T15:37:11Z)
• Online scalable Gaussian processes with conformal prediction for guaranteed coverage [32.21093722162573]
  The consistency of the resulting uncertainty values hinges on the premise that the learning function conforms to the properties specified by the GP model. We propose to wed the GP with the prevailing conformal prediction (CP), a distribution-free post-processing framework that produces it prediction sets with a provably valid coverage.
  arXiv  Detail & Related papers  (2024-10-07T19:22:15Z)
• The Penalized Inverse Probability Measure for Conformal Classification [0.5172964916120902]
  The work introduces the Penalized Inverse Probability (PIP) nonconformity score, and its regularized version RePIP, that allow the joint optimization of both efficiency and informativeness. The work shows how PIP-based conformal classifiers exhibit precisely the desired behavior in comparison with other nonconformity measures and strike a good balance between informativeness and efficiency.
  arXiv  Detail & Related papers  (2024-06-13T07:37:16Z)
• Stratified Prediction-Powered Inference for Hybrid Language Model Evaluation [62.2436697657307]
  Prediction-powered inference (PPI) is a method that improves statistical estimates based on limited human-labeled data. We propose a method called Stratified Prediction-Powered Inference (StratPPI) We show that the basic PPI estimates can be considerably improved by employing simple data stratification strategies.
  arXiv  Detail & Related papers  (2024-06-06T17:37:39Z)
• Conformal Prediction with Learned Features [22.733758606168873]
  We propose Partition Learning Conformal Prediction (PLCP) to improve conditional validity of prediction sets. We implement PLCP efficiently with gradient alternating descent, utilizing off-the-shelf machine learning models. Our experimental results over four real-world and synthetic datasets show the superior performance of PLCP.
  arXiv  Detail & Related papers  (2024-04-26T15:43:06Z)
• Variational Inference with Coverage Guarantees in Simulation-Based Inference [18.818573945984873]
  We propose Conformalized Amortized Neural Variational Inference (CANVI) CANVI constructs conformalized predictors based on each candidate, compares the predictors using a metric known as predictive efficiency, and returns the most efficient predictor. We prove lower bounds on the predictive efficiency of the regions produced by CANVI and explore how the quality of a posterior approximation relates to the predictive efficiency of prediction regions based on that approximation.
  arXiv  Detail & Related papers  (2023-05-23T17:24:04Z)
• Improving Adaptive Conformal Prediction Using Self-Supervised Learning [72.2614468437919]
  We train an auxiliary model with a self-supervised pretext task on top of an existing predictive model and use the self-supervised error as an additional feature to estimate nonconformity scores. We empirically demonstrate the benefit of the additional information using both synthetic and real data on the efficiency (width), deficit, and excess of conformal prediction intervals.
  arXiv  Detail & Related papers  (2023-02-23T18:57:14Z)
• Efficient and Differentiable Conformal Prediction with General Function Classes [96.74055810115456]
  We propose a generalization of conformal prediction to multiple learnable parameters. We show that it achieves approximate valid population coverage and near-optimal efficiency within class. Experiments show that our algorithm is able to learn valid prediction sets and improve the efficiency significantly.
  arXiv  Detail & Related papers  (2022-02-22T18:37:23Z)
• Leveraging Unlabeled Data to Predict Out-of-Distribution Performance [63.740181251997306]
  Real-world machine learning deployments are characterized by mismatches between the source (training) and target (test) distributions. In this work, we investigate methods for predicting the target domain accuracy using only labeled source data and unlabeled target data. We propose Average Thresholded Confidence (ATC), a practical method that learns a threshold on the model's confidence, predicting accuracy as the fraction of unlabeled examples.
  arXiv  Detail & Related papers  (2022-01-11T23:01:12Z)
• Efficient Ensemble Model Generation for Uncertainty Estimation with Bayesian Approximation in Segmentation [74.06904875527556]
  We propose a generic and efficient segmentation framework to construct ensemble segmentation models. In the proposed method, ensemble models can be efficiently generated by using the layer selection method. We also devise a new pixel-wise uncertainty loss, which improves the predictive performance.
  arXiv  Detail & Related papers  (2020-05-21T16:08:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.