Wild refitting for black box prediction

• URL: http://arxiv.org/abs/2506.21460v2
• Date: Tue, 08 Jul 2025 23:47:24 GMT
• Title: Wild refitting for black box prediction
• Authors: Martin J. Wainwright,
• Abstract summary: We describe and analyze a computionally efficient refitting procedure for computing high-probability upper bounds on the instance-wise mean-squared prediction error.<n>Requiring only a single dataset and black box access to the prediction method, it consists of three steps: computing suitable residuals, symmetrizing and scaling them with a pre-factor $rho$, and using them to define and solve a modified prediction problem.
• Score: 29.715181593057803
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We describe and analyze a computionally efficient refitting procedure for computing high-probability upper bounds on the instance-wise mean-squared prediction error of penalized nonparametric estimates based on least-squares minimization. Requiring only a single dataset and black box access to the prediction method, it consists of three steps: computing suitable residuals, symmetrizing and scaling them with a pre-factor $\rho$, and using them to define and solve a modified prediction problem recentered at the current estimate. We refer to it as wild refitting, since it uses Rademacher residual symmetrization as in a wild bootstrap variant. Under relatively mild conditions allowing for noise heterogeneity, we establish a high probability guarantee on its performance, showing that the wild refit with a suitably chosen wild noise scale $\rho$ gives an upper bound on prediction error. This theoretical analysis provides guidance into the design of such procedures, including how the residuals should be formed, the amount of noise rescaling in the wild sub-problem needed for upper bounds, and the local stability properties of the block-box procedure. We illustrate the applicability of this procedure to various problems, including non-rigid structure-from-motion recovery with structured matrix penalties; plug-and-play image restoration with deep neural network priors; and randomized sketching with kernel methods.

Related papers

• Richer Bayesian Last Layers with Subsampled NTK Features [25.566044416945875]
  Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks.<n>We propose a method that improves BLLs by leveraging a projection of Neural Tangent Kernel (NTK) features onto the space spanned by the last-layer features.<n>This enables posterior inference that accounts for variability of the full network while retaining the low computational cost of inference of a standard BLL.
  arXiv  Detail & Related papers  (2026-02-01T15:24:20Z)
• Doubly Wild Refitting: Model-Free Evaluation of High Dimensional Black-Box Predictions under Convex Losses [15.386375612838371]
  We study the problem of excess risk evaluation for empirical risk minimization under general convex loss functions.<n>Our contribution is an efficient refitting procedure that computes the excess risk and provides high-probability upper bounds under the fixed-design setting.
  arXiv  Detail & Related papers  (2025-11-24T05:38:47Z)
• Minimum Volume Conformal Sets for Multivariate Regression [44.99833362998488]
  Conformal prediction provides a principled framework for constructing predictive sets with finite-sample validity.<n>We propose an optimization-driven framework based on a novel loss function that directly learns minimum-conformity covering sets.<n>Our approach optimize over prediction sets defined by arbitrary norm balls, including single and multi-norm formulations.
  arXiv  Detail & Related papers  (2025-03-24T18:54:22Z)
• Decision from Suboptimal Classifiers: Excess Risk Pre- and Post-Calibration [52.70324949884702]
  We quantify the excess risk incurred using approximate posterior probabilities in batch binary decision-making.<n>We identify regimes where recalibration alone addresses most of the regret, and regimes where the regret is dominated by the grouping loss.<n>On NLP experiments, we show that these quantities identify when the expected gain of more advanced post-training is worth the operational cost.
  arXiv  Detail & Related papers  (2025-03-23T10:52:36Z)
• Epistemic Uncertainty in Conformal Scores: A Unified Approach [2.449909275410288]
  Conformal prediction methods create prediction bands with distribution-free guarantees but do not explicitly capture uncertainty.<n>We introduce $texttEPICSCORE$, a model-agnostic approach that enhances any conformal score by explicitly integrating uncertainty.<n>$texttEPICSCORE$ adaptively expands predictive intervals in regions with limited data while maintaining compact intervals where data is abundant.
  arXiv  Detail & Related papers  (2025-02-10T19:42:54Z)
• Can Bayesian Neural Networks Make Confident Predictions? [0.0]
  We show that under a discretized prior for the inner layer weights, we can exactly characterize the posterior predictive distribution as a Gaussian mixture.<n>We also characterize the capacity of a model to "learn from data" by evaluating contraction of the posterior predictive in different scaling regimes.
  arXiv  Detail & Related papers  (2025-01-20T22:36:28Z)
• Accelerated zero-order SGD under high-order smoothness and overparameterized regime [79.85163929026146]
  We present a novel gradient-free algorithm to solve convex optimization problems. Such problems are encountered in medicine, physics, and machine learning. We provide convergence guarantees for the proposed algorithm under both types of noise.
  arXiv  Detail & Related papers  (2024-11-21T10:26:17Z)
• Regression Trees for Fast and Adaptive Prediction Intervals [2.6763498831034043]
  We present a family of methods to calibrate prediction intervals for regression problems with local coverage guarantees. We create a partition by training regression trees and Random Forests on conformity scores. Our proposal is versatile, as it applies to various conformity scores and prediction settings.
  arXiv  Detail & Related papers  (2024-02-12T01:17:09Z)
• Likelihood Ratio Confidence Sets for Sequential Decision Making [51.66638486226482]
  We revisit the likelihood-based inference principle and propose to use likelihood ratios to construct valid confidence sequences. Our method is especially suitable for problems with well-specified likelihoods. We show how to provably choose the best sequence of estimators and shed light on connections to online convex optimization.
  arXiv  Detail & Related papers  (2023-11-08T00:10:21Z)
• Distributionally Robust Optimization with Bias and Variance Reduction [9.341215359733601]
  We show that Prospect, a gradient-based algorithm, enjoys linear convergence for smooth regularized losses. We also show that Prospect can converge 2-3$times$ faster than baselines such as gradient-based methods.
  arXiv  Detail & Related papers  (2023-10-21T00:03:54Z)
• Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability [50.44439018155837]
  We propose to include a calibration term directly into the training objective of the neural model. By introducing a relaxation of the classical formulation of calibration error we enable end-to-end backpropagation. It is directly applicable to existing computational pipelines allowing reliable black-box posterior inference.
  arXiv  Detail & Related papers  (2023-10-20T10:20:45Z)
• Near-optimal inference in adaptive linear regression [60.08422051718195]
  Even simple methods like least squares can exhibit non-normal behavior when data is collected in an adaptive manner. We propose a family of online debiasing estimators to correct these distributional anomalies in at least squares estimation. We demonstrate the usefulness of our theory via applications to multi-armed bandit, autoregressive time series estimation, and active learning with exploration.
  arXiv  Detail & Related papers  (2021-07-05T21:05:11Z)
• Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation [99.92568326314667]
  We propose the amortized conditional normalized maximum likelihood (ACNML) method as a scalable general-purpose approach for uncertainty estimation. Our algorithm builds on the conditional normalized maximum likelihood (CNML) coding scheme, which has minimax optimal properties according to the minimum description length principle. We demonstrate that ACNML compares favorably to a number of prior techniques for uncertainty estimation in terms of calibration on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2020-11-05T08:04:34Z)

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.