English
Related papers

Related papers: A Cram\'er-Rao Type Bound for Bayesian Risk with B…

200 papers

We establish nonuniform Berry-Esseen bounds for martingales under the conditional Bernstein condition. These bounds imply Cram\'er type large deviations for moderate $x$'s, and are of exponential decay rate as de la Pe\~na's inequality when…

Probability · Mathematics 2017-08-03 Xiequan Fan , Ion Grama , Quansheng Liu

This paper considers the quantification of the prediction performance in Gaussian process regression. The standard approach is to base the prediction error bars on the theoretical predictive variance, which is a lower bound on the mean…

Machine Learning · Statistics 2017-03-16 Johan Wågberg , Dave Zachariah , Thomas B. Schön , Petre Stoica

Purpose: To develop neural network (NN)-based quantitative MRI parameter estimators with minimal bias and a variance close to the Cram\'er-Rao bound. Theory and Methods: We generalize the mean squared error loss to control the bias and…

Medical Physics · Physics 2024-05-07 Andrew Mao , Sebastian Flassbeck , Jakob Assländer

In multiparameter quantum metrology, the weighted-arithmetic-mean error of estimation is often used as a scalar cost function to be minimized during design optimization. However, other types of mean error can reveal different facets of…

Quantum Physics · Physics 2020-02-12 Xiao-Ming Lu , Zhihao Ma , Chengjie Zhang

A loss function measures the discrepancy between the true values and their estimated fits, for a given instance of data. In classification problems, a loss function is said to be proper if a minimizer of the expected loss is the true…

Information Theory · Computer Science 2020-01-03 Amichai Painsky , Gregory W. Wornell

The paper introduces scaled Bregman distances of probability distributions which admit non-uniform contributions of observed events. They are introduced in a general form covering not only the distances of discrete and continuous stochastic…

Information Theory · Computer Science 2021-05-12 Wolfgang Stummer , Igor Vajda

Established approaches to obtain generalization bounds in data-driven optimization and machine learning mostly build on solutions from empirical risk minimization (ERM), which depend crucially on the functional complexity of the hypothesis…

Optimization and Control · Mathematics 2022-10-14 Yibo Zeng , Henry Lam

Van Trees inequality, also known as the Bayesian Cram\'er-Rao lower bound, is a powerful tool for establishing lower bounds for minimax estimation through Fisher information. It easily adapts to different statistical models and often yields…

Information Theory · Computer Science 2024-04-30 Wei-Ning Chen , Ayfer Özgür

Several inequalities are presented which, in part, generalize inequalities by Weinstein and Weiss, giving rise to new lower bounds for the Bayes risk under squared error loss.

Information Theory · Computer Science 2014-01-22 Asaf Weinstein , Ehud Weinstein

Adversarial robustness of machine learning models is critical to ensuring reliable performance under data perturbations. Recent progress has been on point estimators, and this paper considers distributional predictors. First, using the link…

Machine Learning · Computer Science 2025-02-21 Mahalakshmi Sabanayagam , Russell Tsuchida , Cheng Soon Ong , Debarghya Ghoshdastidar

We analyze the best achievable performance of Bayesian learning under generative models by defining and upper-bounding the minimum excess risk (MER): the gap between the minimum expected loss attainable by learning from data and the minimum…

Machine Learning · Computer Science 2022-01-04 Aolin Xu , Maxim Raginsky

Information geometry describes a framework where probability densities can be viewed as differential geometry structures. This approach has shown that the geometry in the space of probability distributions that are parameterized by their…

Information Theory · Computer Science 2018-01-16 M. Ashok Kumar , Kumar Vijay Mishra

This paper studies a problem of Bayesian parameter estimation for a sequence of scaled counting processes whose weak limit is a Brownian motion with an unknown drift. The main result of the paper is that the limit of the posterior…

Statistics Theory · Mathematics 2015-03-19 Asaf Cohen

A Cram\'er-type moderate deviation theorem quantifies the relative error of the tail probability approximation. It provides theoretical justification when the limiting tail probability can be used to estimate the tail probability under…

Probability · Mathematics 2021-04-28 Qi-Man Shao , Mengchen Zhang , Zhuo-Song Zhang

In this paper, we present new high-probability PAC-Bayes bounds for different types of losses. Firstly, for losses with a bounded range, we recover a strengthened version of Catoni's bound that holds uniformly for all parameter values. This…

Machine Learning · Statistics 2024-06-05 Borja Rodríguez-Gálvez , Ragnar Thobaben , Mikael Skoglund

We introduce a modified version of the excess risk, which can be used to obtain tighter, fast-rate PAC-Bayesian generalisation bounds. This modified excess risk leverages information about the relative hardness of data examples to reduce…

Machine Learning · Computer Science 2023-01-25 Felix Biggs , Benjamin Guedj

Already since the work by Abbe and Rayleigh the difficulty of super resolution where one wants to recover a collection of point sources from low-resolved microscopy measurements is thought to be dependent on whether the distance between the…

Numerical Analysis · Mathematics 2023-11-07 Mathias Hockmann

This is a tutorial aimed at illustrating some recent developments in quantum parameter estimation beyond the Cram\`er-Rao bound, as well as their applications in quantum metrology. Our starting point is the observation that there are…

Quantum Physics · Physics 2020-03-06 Luigi Seveso , Matteo G. A. Paris

We consider Bayesian shrinkage predictions for the Normal regression problem under the frequentist Kullback-Leibler risk function. Firstly, we consider the multivariate Normal model with an unknown mean and a known covariance. While the…

Statistics Theory · Mathematics 2007-06-13 Kei Kobayashi , Fumiyasu Komaki

Bayesian Optimization (BO) is a data-driven strategy for minimizing/maximizing black-box functions based on probabilistic surrogate models. In the presence of safety constraints, the performance of BO crucially relies on tight probabilistic…

Machine Learning · Statistics 2025-04-15 Oleksii Molodchyk , Johannes Teutsch , Timm Faulwasser
‹ Prev 1 3 4 5 6 7 10 Next ›