Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts

• URL: http://arxiv.org/abs/2605.02072v1
• Date: Sun, 03 May 2026 22:01:19 GMT
• Title: Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts
• Abstract summary: We introduce clipped least-squares importance fitting as a reduced-variance method for density ratio estimation.<n>We show that density ratios learned using CLISF, when plugged into WCP, have bounded expected undercoverage.<n>We provide the first theoretical guarantees for weight clipping in conformal inference.
• Score: 16.253156035425057
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Conformal prediction (CP) provides powerful, distribution-free prediction sets, but its guarantees rely on the exchangeability of training and test data, which is often violated in practice due to covariate shifts. While weighted conformal prediction (WCP) is designed to handle such shifts, it can suffer from significant undercoverage when the density ratio between the distributions is unbounded and/or must be learned. This is because of both overfitting in learning the density ratio, and high variance in estimating the nonconformity score threshold. To address this, we introduce clipped least-squares importance fitting (CLISF) as a reduced-variance method for density ratio estimation. Specifically, we show that density ratios learned using CLISF, when plugged into WCP, have bounded expected undercoverage. Furthermore, we show that the undercoverage can be corrected by running WCP with a slightly inflated coverage target; crucially, we are able to estimate the required level of inflation from the data. We provide the first theoretical guarantees for weight clipping in conformal inference, achieving dataset-conditional coverage with a sample complexity that does not blow up with the higher moments of the true density ratio -- a key limitation of prior work. We verify our results on real-world benchmarks and synthetic data.

Related papers

• Nonparametric Goodness-of-fit Testing under Covariate Shift [4.3686879183724665]
  The distribution mismatch is quantified by either a bounded moment condition or a sub-exponential tail condition on the target-to-source density ratio.<n>Our method combines truncated importance-weighting kernel ridge regression with a multiplier bootstrap to construct confidence sets for the regression function.<n>We prove nonasymptotic validity and sharpness of the resulting confidence sets under suitable operator compatibility conditions.
  arXiv  Detail & Related papers  (2026-08-05T13:51:43Z)
• Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation [55.47411235954028]
  We recast imputation under missing completely at random as density estimation from masked observations.<n>We obtain a convex empirical risk problem with closed form marginals, solvable by a Newton interior point method.<n>The resulting PSD Impute model yields both single and multiple imputations from the same fitted density.
  arXiv  Detail & Related papers  (2026-07-08T15:51:05Z)
• Density-Ratio Losses for Post-Hoc Learning to Defer [61.81110533670321]
  We study post-hoc Learning to Defer (L2D) through the lens of ideal distributions.<n>We define deferral via the density-ratio between a model's and an expert's ideals.<n>Deferral decisions are then made by thresholding the scorer, allowing deferral rates to be adjusted without retraining.
  arXiv  Detail & Related papers  (2026-05-19T08:56:23Z)
• Unbounded Density Ratio Estimation and Its Application to Covariate Shift Adaptation [6.455982311339433]
  unbounded density ratio estimation is an understudied yet critical challenge in statistical learning.<n>Much of the existing literature assumes that the density ratio is either uniformly bounded or unbounded but known exactly.<n>We propose a three-step estimation method that leverages unlabeled data from both the source and target distributions.
  arXiv  Detail & Related papers  (2026-03-31T13:24:50Z)
• ST-BCP: Tightening Coverage Bound for Backward Conformal Prediction via Non-Conformity Score Transformation [18.272247805086284]
  Conformal Prediction (CP) provides a statistical framework for uncertainty quantification that constructs prediction sets with coverage guarantees.<n>BCP inverts this paradigm by enforcing a predefined upper bound on set size and estimating the resulting coverage guarantee.<n>We introduce ST-BCP, a novel method that introduces a data-dependent transformation of nonconformity scores to narrow the coverage gap.
  arXiv  Detail & Related papers  (2026-02-02T07:18:35Z)
• Colorful Pinball: Density-Weighted Quantile Regression for Conditional Guarantee of Conformal Prediction [7.273442425568326]
  We refine the quantile regression components that underpin many conformal methods.<n>We provide a theoretical analysis with exact non-asymptotic guarantees characterizing the resulting excess risk.<n>Experiments on diverse high-dimensional real-world datasets demonstrate remarkable improvements in conditional coverage performance.
  arXiv  Detail & Related papers  (2025-12-30T11:02:35Z)
• Federated Conditional Conformal Prediction via Generative Models [12.463514743585515]
  Conformal Prediction (CP) provides distribution-free uncertainty quantification.<n>Fed Conditional Conformal Prediction (Fed-CCP) aims for conditional coverage that adapts to local data heterogeneity.<n> Experiments on real datasets demonstrate that Fed-CCP achieves more adaptive prediction sets.
  arXiv  Detail & Related papers  (2025-10-15T08:38:38Z)
• COIN: Uncertainty-Guarding Selective Question Answering for Foundation Models with Provable Risk Guarantees [51.5976496056012]
  COIN is an uncertainty-guarding selection framework that calibrates statistically valid thresholds to filter a single generated answer per question.<n>COIN estimates the empirical error rate on a calibration set and applies confidence interval methods to establish a high-probability upper bound on the true error rate.<n>We demonstrate COIN's robustness in risk control, strong test-time power in retaining admissible answers, and predictive efficiency under limited calibration data.
  arXiv  Detail & Related papers  (2025-06-25T07:04:49Z)
• Provably Reliable Conformal Prediction Sets in the Presence of Data Poisoning [53.42244686183879]
  Conformal prediction provides model-agnostic and distribution-free uncertainty quantification.<n>Yet, conformal prediction is not reliable under poisoning attacks where adversaries manipulate both training and calibration data.<n>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)
• Kernel-based Optimally Weighted Conformal Prediction Intervals [12.814084012624916]
  We present Kernel-based Optimally Weighted Conformal Prediction Intervals (KOWCPI)<n>KOWCPI adapts the classic Reweighted Nadaraya-Watson (RNW) estimator for quantile regression on dependent data and learns optimal data-adaptive weights.<n>We demonstrate the superior performance of KOWCPI on real and synthetic time-series data against state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-05-27T04:49:41Z)
• Federated Conformal Predictors for Distributed Uncertainty Quantification [83.50609351513886]
  Conformal prediction is emerging as a popular paradigm for providing rigorous uncertainty quantification in machine learning. In this paper, we extend conformal prediction to the federated learning setting. We propose a weaker notion of partial exchangeability, better suited to the FL setting, and use it to develop the Federated Conformal Prediction framework.
  arXiv  Detail & Related papers  (2023-05-27T19:57:27Z)
• On the Practicality of Differential Privacy in Federated Learning by Tuning Iteration Times [51.61278695776151]
  Federated Learning (FL) is well known for its privacy protection when training machine learning models among distributed clients collaboratively. Recent studies have pointed out that the naive FL is susceptible to gradient leakage attacks. Differential Privacy (DP) emerges as a promising countermeasure to defend against gradient leakage attacks.
  arXiv  Detail & Related papers  (2021-01-11T19:43:12Z)

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.