Estimation of the Learning Coefficient Using Empirical Loss

• URL: http://arxiv.org/abs/2502.09998v1
• Date: Fri, 14 Feb 2025 08:30:04 GMT
• Title: Estimation of the Learning Coefficient Using Empirical Loss
• Authors: Tatsuyoshi Takio, Joe Suzuki,
• Abstract summary: The learning coefficient plays a crucial role in analyzing the performance of information criteria. We propose a novel numerical estimation method that fundamentally differs from previous approaches.
• Score: 0.9208007322096532
• License:
• Abstract: The learning coefficient plays a crucial role in analyzing the performance of information criteria, such as the Widely Applicable Information Criterion (WAIC) and the Widely Applicable Bayesian Information Criterion (WBIC), which Sumio Watanabe developed to assess model generalization ability. In regular statistical models, the learning coefficient is given by d/2, where d is the dimension of the parameter space. More generally, it is defined as the absolute value of the pole order of a zeta function derived from the Kullback-Leibler divergence and the prior distribution. However, except for specific cases such as reduced-rank regression, the learning coefficient cannot be derived in a closed form. Watanabe proposed a numerical method to estimate the learning coefficient, which Imai further refined to enhance its convergence properties. These methods utilize the asymptotic behavior of WBIC and have been shown to be statistically consistent as the sample size grows. In this paper, we propose a novel numerical estimation method that fundamentally differs from previous approaches and leverages a new quantity, "Empirical Loss," which was introduced by Watanabe. Through numerical experiments, we demonstrate that our proposed method exhibits both lower bias and lower variance compared to those of Watanabe and Imai. Additionally, we provide a theoretical analysis that elucidates why our method outperforms existing techniques and present empirical evidence that supports our findings.

Related papers

• Model-free Methods for Event History Analysis and Efficient Adjustment (PhD Thesis) [55.2480439325792]
  This thesis is a series of independent contributions to statistics unified by a model-free perspective. The first chapter elaborates on how a model-free perspective can be used to formulate flexible methods that leverage prediction techniques from machine learning. The second chapter studies the concept of local independence, which describes whether the evolution of one process is directly influenced by another.
  arXiv  Detail & Related papers  (2025-02-11T19:24:09Z)
• Method-of-Moments Inference for GLMs and Doubly Robust Functionals under Proportional Asymptotics [30.324051162373973]
  We consider the estimation of regression coefficients and signal-to-noise ratio in high-dimensional Generalized Linear Models (GLMs) We derive Consistent and Asymptotically Normal (CAN) estimators of our targets of inference. We complement our theoretical results with numerical experiments and comparisons with existing literature.
  arXiv  Detail & Related papers  (2024-08-12T12:43:30Z)
• Model Free Prediction with Uncertainty Assessment [7.524024486998338]
  We propose a novel framework that transforms the deep estimation paradigm into a platform conducive to conditional mean estimation. We develop an end-to-end convergence rate for the conditional diffusion model and establish the normality of the generated samples. Through numerical experiments, we empirically validate the efficacy of our proposed methodology.
  arXiv  Detail & Related papers  (2024-05-21T11:19:50Z)
• Selective Nonparametric Regression via Testing [54.20569354303575]
  We develop an abstention procedure via testing the hypothesis on the value of the conditional variance at a given point. Unlike existing methods, the proposed one allows to account not only for the value of the variance itself but also for the uncertainty of the corresponding variance predictor.
  arXiv  Detail & Related papers  (2023-09-28T13:04:11Z)
• Non-Parametric Learning of Stochastic Differential Equations with Non-asymptotic Fast Rates of Convergence [65.63201894457404]
  We propose a novel non-parametric learning paradigm for the identification of drift and diffusion coefficients of non-linear differential equations. The key idea essentially consists of fitting a RKHS-based approximation of the corresponding Fokker-Planck equation to such observations.
  arXiv  Detail & Related papers  (2023-05-24T20:43:47Z)
• Data-Driven Influence Functions for Optimization-Based Causal Inference [105.5385525290466]
  We study a constructive algorithm that approximates Gateaux derivatives for statistical functionals by finite differencing. We study the case where probability distributions are not known a priori but need to be estimated from data.
  arXiv  Detail & Related papers  (2022-08-29T16:16:22Z)
• A New Central Limit Theorem for the Augmented IPW Estimator: Variance Inflation, Cross-Fit Covariance and Beyond [0.9172870611255595]
  Cross-fit inverse probability weighting (AIPW) with cross-fitting is a popular choice in practice. We study this cross-fit AIPW estimator under well-specified outcome regression and propensity score models in a high-dimensional regime. Our work utilizes a novel interplay between three distinct tools--approximate message passing theory, the theory of deterministic equivalents, and the leave-one-out approach.
  arXiv  Detail & Related papers  (2022-05-20T14:17:53Z)
• Learning to Estimate Without Bias [57.82628598276623]
  Gauss theorem states that the weighted least squares estimator is a linear minimum variance unbiased estimation (MVUE) in linear models. In this paper, we take a first step towards extending this result to non linear settings via deep learning with bias constraints. A second motivation to BCE is in applications where multiple estimates of the same unknown are averaged for improved performance.
  arXiv  Detail & Related papers  (2021-10-24T10:23:51Z)
• Statistical Inference for High-Dimensional Linear Regression with Blockwise Missing Data [13.48481978963297]
  Blockwise missing data occurs when we integrate multisource or multimodality data where different sources or modalities contain complementary information. We propose a computationally efficient estimator for the regression coefficient vector based on carefully constructed unbiased estimating equations. Numerical studies and application analysis of the Alzheimer's Disease Neuroimaging Initiative data show that the proposed method performs better and benefits more from unsupervised samples than existing methods.
  arXiv  Detail & Related papers  (2021-06-07T05:12:42Z)
• Statistical learning and cross-validation for point processes [0.9281671380673306]
  This paper presents the first general (parametric) statistical learning framework for point processes in general spaces. The general idea is to carry out the fitting by predicting CV-generated validation sets using the corresponding training sets. We numerically show that our statistical learning approach outperforms the state of the art in terms of mean (integrated) squared error.
  arXiv  Detail & Related papers  (2021-03-01T23:47:48Z)
• Leveraging Global Parameters for Flow-based Neural Posterior Estimation [90.21090932619695]
  Inferring the parameters of a model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e., when distinct sets of parameters yield identical observations. We present a method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters.
  arXiv  Detail & Related papers  (2021-02-12T12:23:13Z)

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.