On relative universality, regression operator, and conditional independence

• URL: http://arxiv.org/abs/2504.11044v1
• Date: Tue, 15 Apr 2025 10:12:26 GMT
• Title: On relative universality, regression operator, and conditional independence
• Authors: Bing Li, Ben Jones, Andreas Artemiou,
• Abstract summary: We modify the definition of relative universality using the concept of ko-measurability.<n>The significance of this result is beyond its original context of sufficient dimension reduction.
• Score: 3.4759820813589966
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The notion of relative universality with respect to a {\sigma}-field was introduced to establish the unbiasedness and Fisher consistency of an estimator in nonlinear sufficient dimension reduction. However, there is a gap in the proof of this result in the existing literature. The existing definition of relative universality seems to be too strong for the proof to be valid. In this note we modify the definition of relative universality using the concept of \k{o}-measurability, and rigorously establish the mentioned unbiasedness and Fisher consistency. The significance of this result is beyond its original context of sufficient dimension reduction, because relative universality allows us to use the regression operator to fully characterize conditional independence, a crucially important statistical relation that sits at the core of many areas and methodologies in statistics and machine learning, such as dimension reduction, graphical models, probability embedding, causal inference, and Bayesian estimation.

Related papers

• Advancing Counterfactual Inference through Nonlinear Quantile Regression [77.28323341329461]
  We propose a framework for efficient and effective counterfactual inference implemented with neural networks. The proposed approach enhances the capacity to generalize estimated counterfactual outcomes to unseen data. Empirical results conducted on multiple datasets offer compelling support for our theoretical assertions.
  arXiv  Detail & Related papers  (2023-06-09T08:30:51Z)
• Bayesian Renormalization [68.8204255655161]
  We present a fully information theoretic approach to renormalization inspired by Bayesian statistical inference. The main insight of Bayesian Renormalization is that the Fisher metric defines a correlation length that plays the role of an emergent RG scale. We provide insight into how the Bayesian Renormalization scheme relates to existing methods for data compression and data generation.
  arXiv  Detail & Related papers  (2023-05-17T18:00:28Z)
• A Robustness Analysis of Blind Source Separation [91.3755431537592]
  Blind source separation (BSS) aims to recover an unobserved signal from its mixture $X=f(S)$ under the condition that the transformation $f$ is invertible but unknown. We present a general framework for analysing such violations and quantifying their impact on the blind recovery of $S$ from $X$. We show that a generic BSS-solution in response to general deviations from its defining structural assumptions can be profitably analysed in the form of explicit continuity guarantees.
  arXiv  Detail & Related papers  (2023-03-17T16:30:51Z)
• A Universal Formulation of Uncertainty Relation for Error-Disturbance and Local Representability of Quantum Observables [1.696974372855528]
  A universal formulation of the quantum uncertainty regarding quantum indeterminacy, quantum measurement, and its inevitable observer effect is presented. The framework assures that the resultant general relations admit natural operational interpretations and characterisations.
  arXiv  Detail & Related papers  (2022-04-25T17:44:21Z)
• Universal Regression with Adversarial Responses [26.308541799686505]
  We provide algorithms for regression with adversarial responses under large classes of non-i.i.d. instance sequences. We consider universal consistency which asks for strong consistency of a learner without restrictions on the value responses.
  arXiv  Detail & Related papers  (2022-03-09T22:10:30Z)
• Non-Linear Spectral Dimensionality Reduction Under Uncertainty [107.01839211235583]
  We propose a new dimensionality reduction framework, called NGEU, which leverages uncertainty information and directly extends several traditional approaches. We show that the proposed NGEU formulation exhibits a global closed-form solution, and we analyze, based on the Rademacher complexity, how the underlying uncertainties theoretically affect the generalization ability of the framework.
  arXiv  Detail & Related papers  (2022-02-09T19:01:33Z)
• Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification [58.03725169462616]
  We show theoretically that over-parametrization is not the only reason for over-confidence. We prove that logistic regression is inherently over-confident, in the realizable, under-parametrized setting. Perhaps surprisingly, we also show that over-confidence is not always the case.
  arXiv  Detail & Related papers  (2021-02-15T21:38:09Z)
• Uniqueness of noncontextual models for stabilizer subtheories [0.0]
  We give a complete characterization of the (non)classicality of all stabilizer subtheories. We prove that there is a unique nonnegative and diagram-preserving quasiprobability representation of the stabilizer subtheory in all odd dimensions.
  arXiv  Detail & Related papers  (2021-01-15T18:54:58Z)
• A Universal Formulation of Uncertainty Relation for Error and Disturbance [0.9479435599284545]
  We present a universal formulation of uncertainty relation valid for any conceivable quantum measurement. Owing to its simplicity and operational tangibility, our general relation is also experimentally verifiable.
  arXiv  Detail & Related papers  (2020-04-13T17:57:41Z)
• GenDICE: Generalized Offline Estimation of Stationary Values [108.17309783125398]
  We show that effective estimation can still be achieved in important applications. Our approach is based on estimating a ratio that corrects for the discrepancy between the stationary and empirical distributions. The resulting algorithm, GenDICE, is straightforward and effective.
  arXiv  Detail & Related papers  (2020-02-21T00:27:52Z)
• Geometric Formulation of Universally Valid Uncertainty Relation for Error [1.696974372855528]
  We present a new geometric formulation of uncertainty relation valid for any quantum measurements of statistical nature. Owing to its simplicity and tangibility, our relation is universally valid and experimentally viable.
  arXiv  Detail & Related papers  (2020-02-10T18:31:54Z)

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.