E-statistics, group invariance and anytime-valid testing
MF Pérez-Ortiz, T Lardy, R de Heide… - The Annals of …, 2024 - projecteuclid.org
E-statistics, group invariance and anytime-valid testing Page 1 The Annals of Statistics 2024,
Vol. 52, No. 4, 1410–1432 https://doi.org/10.1214/24-AOS2394 © Institute of Mathematical …
Vol. 52, No. 4, 1410–1432 https://doi.org/10.1214/24-AOS2394 © Institute of Mathematical …
Minimum description length tutorial
P Grünwald - 2005 - direct.mit.edu
In Chapter 1 we introduced the minimum description length (MDL) Principle in an informal
way. In this chapter we give an introduction to MDL that is mathematically precise …
way. In this chapter we give an introduction to MDL that is mathematically precise …
[图书][B] Shrinkage estimation
D Fourdrinier, WE Strawderman, MT Wells - 2018 - Springer
Starting in the 1930s, a mathematically rigorous approach to frequentist statistical inference,
now called statistical decision theory, was introduced by Jerzy Neyman, Egon Pearson, and …
now called statistical decision theory, was introduced by Jerzy Neyman, Egon Pearson, and …
Improved minimax predictive densities under Kullback–Leibler loss
Abstract Let X| μ∼ N p (μ, vx I) and Y| μ∼ N p (μ, vy I) be independent p-dimensional
multivariate normal vectors with common unknown mean μ. Based on only observing X= x …
multivariate normal vectors with common unknown mean μ. Based on only observing X= x …
An improper estimator with optimal excess risk in misspecified density estimation and logistic regression
J Mourtada, S Gaïffas - Journal of Machine Learning Research, 2022 - jmlr.org
We introduce a procedure for conditional density estimation under logarithmic loss, which
we call SMP (Sample Minmax Predictor). This estimator minimizes a new general excess …
we call SMP (Sample Minmax Predictor). This estimator minimizes a new general excess …
Admissible predictive density estimation
LD Brown, EI George, X Xu - 2008 - projecteuclid.org
Abstract Let X| μ∼ N p (μ, vx I) and Y| μ∼ N p (μ, vy I) be independent p-dimensional
multivariate normal vectors with common unknown mean μ. Based on observing X= x, we …
multivariate normal vectors with common unknown mean μ. Based on observing X= x, we …
MDL denoising revisited
T Roos, P Myllymaki, J Rissanen - IEEE Transactions on Signal …, 2009 - ieeexplore.ieee.org
We refine and extend an earlier minimum description length (MDL) denoising criterion for
wavelet-based denoising. We start by showing that the denoising problem can be …
wavelet-based denoising. We start by showing that the denoising problem can be …
Bayesian network structure learning using factorized NML universal models
T Roos, T Silander, P Kontkanen… - … Information Theory and …, 2008 - ieeexplore.ieee.org
Universal codes/models can be used for data compression and model selection by the
minimum description length (MDL) principle. For many interesting model classes, such as …
minimum description length (MDL) principle. For many interesting model classes, such as …
Parzen neural networks: Fundamentals, properties, and an application to forensic anthropology
E Trentin, L Lusnig, F Cavalli - Neural Networks, 2018 - Elsevier
A novel, unsupervised nonparametric model of multivariate probability density functions
(pdf) is introduced, namely the Parzen neural network (PNN). The PNN is intended to …
(pdf) is introduced, namely the Parzen neural network (PNN). The PNN is intended to …