English
Related papers

Related papers: Asymptotic Behavior of Bayesian Generalization Err…

200 papers

Predictive dynamical models for marine ecosystems are used for a variety of needs. Due to sparse measurements and limited understanding of the myriad of ocean processes, there is however significant uncertainty. There is model uncertainty…

Computational Engineering, Finance, and Science · Computer Science 2023-06-06 Abhinav Gupta , Pierre F. J. Lermusiaux

Information criteria, such as Akaike's information criterion and Bayesian information criterion are often applied in model selection. However, their asymptotic behaviors for selecting geostatistical regression models have not been well…

Statistics Theory · Mathematics 2014-12-03 Chih-Hao Chang , Hsin-Cheng Huang , Ching-Kang Ing

In data science and machine learning, hierarchical parametric models, such as mixture models, are often used. They contain two kinds of variables: observable variables, which represent the parts of the data that can be directly measured,…

Machine Learning · Statistics 2015-04-20 Keisuke Yamazaki

Electronic structure calculations are ubiquitous in most branches of chemistry, but all have errors in both energies and equilibrium geometries. Quantifying errors in possibly dozens of bond angles and bond lengths is a Herculean task. A…

Chemical Physics · Physics 2020-07-31 Stefan Vuckovic , Kieron Burke

Gaussian mixtures are commonly used for modeling heavy-tailed error distributions in robust linear regression. Combining the likelihood of a multivariate robust linear regression model with a standard improper prior distribution yields an…

Statistics Theory · Mathematics 2023-01-05 Haoxiang Li , Qian Qin , Galin L. Jones

Generalization is a central concept in machine learning theory, yet for quantum models, it is predominantly analyzed through uniform bounds that depend on a model's overall capacity rather than the specific function learned. These…

Statistics comes in two main flavors: frequentist and Bayesian. For historical and technical reasons, frequentist statistics have traditionally dominated empirical data analysis, and certainly remain prevalent in empirical software…

Software Engineering · Computer Science 2024-10-03 Carlo A. Furia , Robert Feldt , Richard Torkar

Asymmetric statistical errors arise for experimental results obtained by Maximum Likelihood estimation, in cases where the number of results is finite and the log likelihood function is not a symmetric parabola. This note discusses how…

Data Analysis, Statistics and Probability · Physics 2007-05-23 Roger Barlow

There is increasing interest in broad application areas in defining flexible joint models for data having a variety of measurement scales, while also allowing data of complex types, such as functions, images and documents. We consider a…

Methodology · Statistics 2013-03-05 Anjishnu Banerjee , Jared Murray , David B. Dunson

Understanding and accurately following instructions is critical for large language models (LLMs) to be effective across diverse tasks. In this work, we rigorously examine the key factors that enable models to generalize to unseen…

Computation and Language · Computer Science 2024-10-21 Dylan Zhang , Justin Wang , Francois Charton

This article is a review of theoretical advances in the research field of algebraic geometry and Bayesian statistics in the last two decades. Many statistical models and learning machines which contain hierarchical structures or latent…

Statistics Theory · Mathematics 2022-11-21 Sumio Watanabe

This work establishes regularity conditions for consistency and asymptotic normality of the multiple parameter maximum likelihood estimator(MLE) from censored data, where the censoring mechanism is in the form of $1$-bit measurements. The…

Statistics Theory · Mathematics 2025-02-11 Jaimin Shah , Martina Cardone , Cynthia Rush , Alex Dytso

Mixture models provide a flexible representation of heterogeneity in a finite number of latent classes. From the Bayesian point of view, Markov Chain Monte Carlo methods provide a way to draw inferences from these models. In particular,…

Methodology · Statistics 2020-05-06 Carolina Valani Cavalcante , Kelly Cristina Mota Gonçalves

We investigate the existence of a fundamental computation-information gap for the problem of clustering a mixture of isotropic Gaussian in the high-dimensional regime, where the ambient dimension $p$ is larger than the number $n$ of points.…

Statistics Theory · Mathematics 2024-02-29 Bertrand Even , Christophe Giraud , Nicolas Verzelen

Data augmentation is one of the most widely used techniques to improve generalization in modern machine learning, often justified by its ability to promote invariance to label-irrelevant transformations. However, its theoretical role…

Machine Learning · Computer Science 2026-02-17 Abdelali Bouyahia , Frédéric LeBlanc , Mario Marchand

Model-independent search strategies have been increasingly proposed in recent years because on the one hand there has been no clear signal for new physics and on the other hand there is a lack of a highly probable and parameter-free…

High Energy Physics - Phenomenology · Physics 2023-03-22 Sascha Caron , Roberto Ruiz de Austri , Zhongyi Zhang

We consider regression models involving multilayer perceptrons (MLP) with one hidden layer and a Gaussian noise. The estimation of the parameters of the MLP can be done by maximizing the likelihood of the model. In this framework, it is…

Statistics Theory · Mathematics 2008-02-25 Joseph Rynkiewicz

In this paper we study the asymptotic properties of Bayesian multiple testing procedures for a large class of Gaussian scale mixture pri- ors. We study two types of multiple testing risks: a Bayesian risk proposed in Bogdan et al. (2011)…

Statistics Theory · Mathematics 2017-11-27 Jean-Bernard Salomond

Coarse graining techniques play an essential role in accelerating molecular simulations of systems with large length and time scales. Theoretically grounded bottom-up models are appealing due to their thermodynamic consistency with the…

Computational Physics · Physics 2022-11-01 Blake R. Duschatko , Jonathan Vandermause , Nicola Molinari , Boris Kozinsky

One of the most surprising and exciting discoveries in supervised learning was the benefit of overparameterization (i.e. training a very large model) to improving the optimization landscape of a problem, with minimal effect on statistical…

Machine Learning · Statistics 2020-07-17 Rares-Darius Buhai , Yoni Halpern , Yoon Kim , Andrej Risteski , David Sontag
‹ Prev 1 8 9 10 Next ›