Stopping Reliability in Adaptive Krylov-Shadow Quantum Fisher Information Estimation

• URL: http://arxiv.org/abs/2605.14338v1
• Date: Thu, 14 May 2026 04:02:23 GMT
• Title: Stopping Reliability in Adaptive Krylov-Shadow Quantum Fisher Information Estimation
• Abstract summary: Adaptive quantum Fisher information (QFI) estimation requires a stopping rule that distinguishes accuracy from apparent numerical stability.<n>We show that a width-only empirical stopping rule, based on interval width and local Krylov stability, can declare convergence at small $(K,M)$ even when the post hoc error exceeds the requested tolerance.
• Score: 0.0
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Adaptive quantum Fisher information (QFI) estimation requires a stopping rule that distinguishes accuracy from apparent numerical stability. For Krylov-shadow QFI estimators, finite Krylov order $K$ produces truncation bias, while finite sample budget $M$ produces finite-$M$ sampling-side error. We show that a width-only empirical stopping rule, based on interval width and local Krylov stability, can declare convergence at small $(K,M)$ even when the post hoc error exceeds the requested tolerance; we call this event a \emph{false stop}. The mechanism is a narrow empirical interval centered on a biased low-$K$ estimate. We give a two-component stopping analysis that separates the Krylov and sampling terms, and we implement a guarded rule that permits a success declaration only after minimum thresholds in $K$ and $M$ and a persistence condition are satisfied. On a five-level dephasing benchmark at $n=4$ qubits, the guarded rule suppresses the false success declarations produced by the width-only empirical rule, whose false-stop rates range from $0.16$ to $0.68$ across the tested noise levels. Under the main fixed resource limit, the guarded rule refuses to make success declarations rather than accepting biased low-$K$ estimates; a separate true-relative-tolerance sampling-budget sequence then shows that, after Krylov and sampling recalibration, the same decision principle can make success declarations without observed false stops. These results show that stopping reliability is a distinct design requirement for adaptive QFI estimation: sampling precision at fixed $K$ does not by itself establish that Krylov truncation bias is controlled.

Related papers

• $TCP_α$: Margin-Controlled Confidence estimation for reliable Music Information Retrieval [7.679660052685777]
  Deep neural networks are often overconfident, assigning high confidence even to incorrect predictions.<n>Existing targets suffer from inherent ambiguity: they assign overlapping confidence values to correct and incorrect predictions, while errors near the decision boundary receive confidence scores indistinguishable from correct predictions.<n>We propose $ TCP_$, a novel confidence target that resolves these limitations by introducing a margin-controlled penalty for misclassified samples.
  arXiv  Detail & Related papers  (2026-08-20T17:58:50Z)
• CASP: Learning-Augmented Offline Approximation with Verifiable Certificates and Bounded-Loss PAC Guarantees [1.7545090618311434]
  Machine-learned predictions can speed up offline NP-hard optimization, but asking a predictor what to do amounts to asking it to solve the problem.<n> CASP (Certificate-Augmented Solution Pruning) instead asks which parts of the search space may be ignored, and accepts each answer only after a sound-time verifier has checked it.<n>With trained predictors, unverified pruning loses up to $26%$ of the optimum under distribution shift, while the verified deployment of the same predictions loses nothing.
  arXiv  Detail & Related papers  (2026-07-16T04:02:15Z)
• Detectability Limits for Intra-Block Temporal Drift in Finite-Key Entanglement-Based QKD [0.0]
  We study the statistical detectability of intra-block temporal drift in finite-key entanglement-based quantum key distribution.<n>Dread is modeled as a mean-preserving Lipschitz perturbation of Bernoulli observables, capturing structured temporal variation.<n>The result quantifies a finite-block monitoring-resolution limit and is distinct from composable security certification.
  arXiv  Detail & Related papers  (2026-05-22T21:18:46Z)
• When to Trust Confidence Thresholding: Calibration Diagnostics for Pseudo-Labelled Regression [1.14219428942199]
  A standard practice is to threshold the calibrated score at a confidence cutoff and treat the hard label as the truth.<n>We develop a calibration-aware diagnostic apparatus for pseudo-labelling pipelines.<n>We derive a closed-form expression for the attenuation bias that confidence thresholding induces in the downstream regression coefficient.
  arXiv  Detail & Related papers  (2026-05-12T21:49:11Z)
• When Are Trade-Off Functions Testable from Finite Samples? [4.706977254727891]
  We study finite-sample inference for the trade-off function of two unknown probability distributions.<n>By inverting the test, we also obtain simultaneous confidence bands for the whole trade-off curve.
  arXiv  Detail & Related papers  (2026-05-11T16:07:48Z)
• Reinforcement Learning Trained Observer Control for Bearings-Only Tracking [0.9167082845109437]
  This paper develops a reinforcement learning based observer control policy for autonomous bearings-only tracking of a moving target.<n>The reward function is designed to address two conflicting objectives: minimising absolute target position estimation error and maintaining CKF estimation consistency.<n>The results show that the DQN policy at $= 0.7$ achieves the best trade-off between accuracy and robustness.
  arXiv  Detail & Related papers  (2026-05-04T00:55:14Z)
• Adaptive Confidence Intervals in Efron's Gaussian Two-Groups Model [28.636700996382558]
  Motivated by noise-oblivious nature of adversaries, we study confidence intervals for the null location parameter $$ in Efron's Gaussian two-groups fraction model.<n>We characterize the minimax-optimal length among confidence intervals with a prescribed coverage level uniformly over the unknown proportion contamination and all noise-oblivious adversaries.
  arXiv  Detail & Related papers  (2026-04-28T22:40:54Z)
• LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems [95.35293543918762]
  Large language models (LLMs) often generate unreliable answers, while uncertainty methods fail to fully distinguish correct from incorrect predictions.<n>We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level.<n>We propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint.
  arXiv  Detail & Related papers  (2025-12-01T11:27:09Z)
• 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)
• Robust Conformal Prediction with a Single Binary Certificate [58.450154976190795]
  Conformal prediction (CP) converts any model's output to prediction sets with a guarantee to cover the true label with (adjustable) high probability.<n>We propose a robust conformal prediction that produces smaller sets even with significantly lower MC samples.
  arXiv  Detail & Related papers  (2025-03-07T08:41:53Z)
• Certified Robust Models with Slack Control and Large Lipschitz Constants [102.69689641398227]
  We propose a Calibrated Lipschitz-Margin Loss (CLL) that addresses two problems. Firstly, commonly used margin losses do not adjust the penalties to the shrinking output distribution. Secondly, minimization of $K$ can lead to overly smooth decision functions. Our CLL addresses these issues by explicitly calibrating the loss w.r.t. margin and Lipschitz constant.
  arXiv  Detail & Related papers  (2023-09-12T12:23:49Z)
• When Does Confidence-Based Cascade Deferral Suffice? [69.28314307469381]
  Cascades are a classical strategy to enable inference cost to vary adaptively across samples. A deferral rule determines whether to invoke the next classifier in the sequence, or to terminate prediction. Despite being oblivious to the structure of the cascade, confidence-based deferral often works remarkably well in practice.
  arXiv  Detail & Related papers  (2023-07-06T04:13:57Z)
• Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness [71.42652863687117]
  We study nonparametric estimation of instrumental variable (IV) regressions. We propose a new penalized minimax estimator that can converge to a fixed IV solution. We derive a strong $L$ error rate for our estimator under lax conditions.
  arXiv  Detail & Related papers  (2023-02-10T18:08:49Z)

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.