English
Related papers

Related papers: Overlap matrix concentration in optimal Bayesian i…

200 papers

Virtually any model we use in machine learning to make predictions does not perfectly represent reality. So, most of the learning happens under model misspecification. In this work, we present a novel analysis of the generalization…

Machine Learning · Computer Science 2020-10-23 Andres R. Masegosa

Subspace inference for neural networks assumes that a subspace of their parameter space suffices to produce a reliable uncertainty quantification. In this work, we underpin the validity of this assumption by using low rank techniques. We…

Machine Learning · Computer Science 2026-04-13 Josua Faller , Jörg Martin

The posterior probability distribution for a set of model parameters encodes all that the data have to tell us in the context of a given model; it is the fundamental quantity for Bayesian parameter estimation. In order to infer the…

Instrumentation and Methods for Astrophysics · Physics 2015-06-16 Rupert Allison , Joanna Dunkley

This work is concerned with the convergence of Gaussian process regression. A particular focus is on hierarchical Gaussian process regression, where hyper-parameters appearing in the mean and covariance structure of the Gaussian process…

Numerical Analysis · Mathematics 2020-07-20 Aretha L Teckentrup

Being able to reliably assess not only the \emph{accuracy} but also the \emph{uncertainty} of models' predictions is an important endeavour in modern machine learning. Even if the model generating the data and labels is known, computing the…

Machine Learning · Computer Science 2023-09-12 Lucas Clarté , Bruno Loureiro , Florent Krzakala , Lenka Zdeborová

Vector approximate message passing (VAMP) is an efficient approximate inference algorithm used for generalized linear models. Although VAMP exhibits excellent performance, particularly when measurement matrices are sampled from rotationally…

Information Theory · Computer Science 2025-08-05 Takashi Takahashi , Yoshiyuki Kabashima

Ising models describe the joint probability distribution of a vector of binary feature variables. Typically, not all the variables interact with each other and one is interested in learning the presumably sparse network structure of the…

Machine Learning · Computer Science 2019-07-09 Frank Nussbaum , Joachim Giesen

In this article a novel approach for training deep neural networks using Bayesian techniques is presented. The Bayesian methodology allows for an easy evaluation of model uncertainty and additionally is robust to overfitting. These are…

Machine Learning · Computer Science 2019-04-03 Konstantin Posch , Jürgen Pilz

Bayesian models are a powerful tool for studying complex data, allowing the analyst to encode rich hierarchical dependencies and leverage prior information. Most importantly, they facilitate a complete characterization of uncertainty…

Machine Learning · Statistics 2023-04-25 Steven Winter , Trevor Campbell , Lizhen Lin , Sanvesh Srivastava , David B. Dunson

The problem of finding a $k \times k$ submatrix of maximum volume of a matrix $A$ is of interest in a variety of applications. For example, it yields a quasi-best low-rank approximation constructed from the rows and columns of $A$. We show…

Numerical Analysis · Mathematics 2019-02-07 Alice Cortinovis , Daniel Kressner , Stefano Massei

It is generally believed that ensemble approaches, which combine multiple algorithms or models, can outperform any single algorithm at machine learning tasks, such as prediction. In this paper, we propose Bayesian convex and linear…

Statistics Theory · Mathematics 2014-03-07 Yun Yang , David B. Dunson

Regularized linear regression is central to machine learning, yet its high-dimensional behavior with informative priors remains poorly understood. We provide the first exact asymptotic characterization of training and test risks for maximum…

Machine Learning · Statistics 2026-01-28 Malik Tiomoko , Ekkehard Schnoor

It is well known that the class of rotation invariant algorithms are suboptimal even for learning sparse linear problems when the number of examples is below the "dimension" of the problem. This class includes any gradient descent trained…

Machine Learning · Statistics 2024-03-06 Manfred K. Warmuth , Wojciech Kotłowski , Matt Jones , Ehsan Amid

We study the asymptotic behaviour of the posterior distribution in a broad class of statistical models where the "true" solution occurs on the boundary of the parameter space. We show that in this case Bayesian inference is consistent, and…

Statistics Theory · Mathematics 2014-10-02 Natalia A. Bochkina , Peter J. Green

Matrix completion and robust principal component analysis have been widely used for the recovery of data suffering from missing entries or outliers. In many real-world applications however, the data is also time-varying, and the naive…

Signal Processing · Electrical Eng. & Systems 2019-06-25 Charul , Uttkarsha Bhatt , Pravesh Biyani , Ketan Rajawat

We propose a novel approach to estimating the precision matrix of multivariate Gaussian data that relies on decomposing them into a low-rank and a diagonal component. Such decompositions are very popular for modeling large covariance…

Methodology · Statistics 2022-08-18 Noirrit Kiran Chandra , Peter Mueller , Abhra Sarkar

We introduce a Bayesian model for inferring mixtures of subspaces of different dimensions. The key challenge in such a mixture model is specification of prior distributions over subspaces of different dimensions. We address this challenge…

Statistics Theory · Mathematics 2015-09-24 Brian St. Thomas , Lizhen Lin , Lek-Heng Lim , Sayan Mukherjee

Bayesian Networks (BNs) represent conditional probability relations among a set of random variables (nodes) in the form of a directed acyclic graph (DAG), and have found diverse applications in knowledge discovery. We study the problem of…

Optimization and Control · Mathematics 2022-05-10 Simge Kucukyavuz , Ali Shojaie , Hasan Manzour , Linchuan Wei , Hao-Hsiang Wu

A Bayesian network is a widely used probabilistic graphical model with applications in knowledge discovery and prediction. Learning a Bayesian network (BN) from data can be cast as an optimization problem using the well-known…

Artificial Intelligence · Computer Science 2018-11-14 Zhenyu A. Liao , Charupriya Sharma , James Cussens , Peter van Beek

We provide finite-sample distribution approximations, that are uniform in the parameter, for inference in linear mixed models. Focus is on variances and covariances of random effects in cases where existing theory fails because their…

Statistics Theory · Mathematics 2025-07-29 Karl Oskar Ekvall , Matteo Bottai