Computational and Statistical Hardness of Calibration Distance

• URL: http://arxiv.org/abs/2603.18391v1
• Date: Thu, 19 Mar 2026 01:21:52 GMT
• Title: Computational and Statistical Hardness of Calibration Distance
• Abstract summary: The distance from calibration has emerged as a central measure of miscalibration for probabilistic predictors.<n>We give an efficient algorithm that exactly computes the calibration distance when the distribution has a uniform marginal and noiseless labels.<n>Perhaps surprisingly, the problem becomes $mathsfNP-hard when either of two assumptions is removed.
• Score: 5.990174495635325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The distance from calibration, introduced by Błasiok, Gopalan, Hu, and Nakkiran (STOC 2023), has recently emerged as a central measure of miscalibration for probabilistic predictors. We study the fundamental problems of computing and estimating this quantity, given either an exact description of the data distribution or only sample access to it. We give an efficient algorithm that exactly computes the calibration distance when the distribution has a uniform marginal and noiseless labels, which improves the $O(1/\sqrt{|\mathcal{X}|})$ additive approximation of Qiao and Zheng (COLT 2024) for this special case. Perhaps surprisingly, the problem becomes $\mathsf{NP}$-hard when either of the two assumptions is removed. We extend our algorithm to a polynomial-time approximation scheme for the general case. For the estimation problem, we show that $Θ(1/ε^3)$ samples are sufficient and necessary for the empirical calibration distance to be upper bounded by the true distance plus $ε$. In contrast, a polynomial dependence on the domain size -- incurred by the learning-based baseline -- is unavoidable for two-sided estimation. Our positive results are based on simple sparsifications of both the distribution and the target predictor, which significantly reduce the search space for computation and lead to stronger concentration for the estimation problem. To prove the hardness results, we introduce new techniques for certifying lower bounds on the calibration distance -- a problem that is hard in general due to its $\textsf{co-NP}$-completeness.

Related papers

• Provably Adaptive Linear Approximation for the Shapley Value and Beyond [73.0940890296463]
  A fundamental and long-standing challenge is their efficient approximation.<n>We develop a linear-space algorithm that requires $P(|hatboldsymbol-boldsymbol|_2geq)leq $ for all commonly used semi-values.<n>Our algorithm allows explicit minimization of the mean square error for each specific utility function.
  arXiv  Detail & Related papers  (2026-04-09T16:38:14Z)
• High-dimensional estimation with missing data: Statistical and computational limits [13.480462575790334]
  We consider computationally-efficient estimation of population parameters when observations are subject to missing data.<n>For mean estimation in $ell$ norm, we show that in order to obtain error at most $$, for any constant contamination $in (0, 1)$, (roughly) $n gtrsim d e1/2$ samples are necessary.<n>We turn to linear regression with missing observations and show that such a gap does not persist.
  arXiv  Detail & Related papers  (2026-03-17T16:02:41Z)
• Closing the Approximation Gap of Partial AUC Optimization: A Tale of Two Formulations [121.39938773554523]
  The Area Under the ROC Curve (AUC) is a pivotal evaluation metric in real-world scenarios with both class imbalance and decision constraints.<n>We present two simple instance-wise minimax reformulations to close the approximation gap of PAUC optimization.<n>The resulting algorithms enjoy a linear per-iteration computational complexity w.r.t. the sample size and a convergence rate of $O(-2/3)$ for typical one-way and two-way PAUCs.
  arXiv  Detail & Related papers  (2025-12-01T02:52:33Z)
• Nearly-Linear Time Private Hypothesis Selection with the Optimal Approximation Factor [9.37782111672415]
  Estimating the density of a distribution from its samples is a fundamental problem in statistics.<n> Hypothesis selection addresses the setting where, in addition to a sample set, we are given $n$ candidate distributions.<n>We propose a differentially private algorithm in the central model that runs in nearly-linear time with respect to the number of hypotheses.
  arXiv  Detail & Related papers  (2025-06-01T20:46:46Z)
• Faster high-accuracy log-concave sampling via algorithmic warm starts [6.117084972237769]
  In practice, high-accuracy samplers such as the classical Metropolis-adjusted Langevin algorithm (MALA) remain the de facto gold standard. We improve the dimension dependence of this sampling problem to $tildeO(d1/2)$, whereas the previous best result for MALA was $tildeO(d)$. Our main technical contribution settles this problem by establishing the first $tildeO(d1/2)$ R'enyi mixing rates for the discretized underdamped Langevin diffusion.
  arXiv  Detail & Related papers  (2023-02-20T19:27:21Z)
• Nystr\"om Kernel Mean Embeddings [92.10208929236826]
  We propose an efficient approximation procedure based on the Nystr"om method. It yields sufficient conditions on the subsample size to obtain the standard $n-1/2$ rate. We discuss applications of this result for the approximation of the maximum mean discrepancy and quadrature rules.
  arXiv  Detail & Related papers  (2022-01-31T08:26:06Z)
• Distributed Sparse Regression via Penalization [5.990069843501885]
  We study linear regression over a network of agents, modeled as an undirected graph (with no centralized node) The estimation problem is formulated as the minimization of the sum of the local LASSO loss functions plus a quadratic penalty of the consensus constraint. We show that the proximal-gradient algorithm applied to the penalized problem converges linearly up to a tolerance of the order of the centralized statistical error.
  arXiv  Detail & Related papers  (2021-11-12T01:51:50Z)
• One-Bit Compressed Sensing via One-Shot Hard Thresholding [7.594050968868919]
  A problem of 1-bit compressed sensing is to estimate a sparse signal from a few binary measurements. We present a novel and concise analysis that moves away from the widely used non-constrained notion of width.
  arXiv  Detail & Related papers  (2020-07-07T17:28:03Z)
• Sample Complexity of Asynchronous Q-Learning: Sharper Analysis and Variance Reduction [63.41789556777387]
  Asynchronous Q-learning aims to learn the optimal action-value function (or Q-function) of a Markov decision process (MDP) We show that the number of samples needed to yield an entrywise $varepsilon$-accurate estimate of the Q-function is at most on the order of $frac1mu_min (1-gamma)5varepsilon2+ fract_mixmu_min (1-gamma)$ up to some logarithmic factor.
  arXiv  Detail & Related papers  (2020-06-04T17:51:00Z)
• Breaking the Sample Size Barrier in Model-Based Reinforcement Learning with a Generative Model [50.38446482252857]
  This paper is concerned with the sample efficiency of reinforcement learning, assuming access to a generative model (or simulator) We first consider $gamma$-discounted infinite-horizon Markov decision processes (MDPs) with state space $mathcalS$ and action space $mathcalA$. We prove that a plain model-based planning algorithm suffices to achieve minimax-optimal sample complexity given any target accuracy level.
  arXiv  Detail & Related papers  (2020-05-26T17:53:18Z)
• Computationally efficient sparse clustering [67.95910835079825]
  We provide a finite sample analysis of a new clustering algorithm based on PCA. We show that it achieves the minimax optimal misclustering rate in the regime $|theta infty$.
  arXiv  Detail & Related papers  (2020-05-21T17:51:30Z)

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.