Query: title:(Leave-One-Out Cross-Validation for Bayesian Model Comparison in Large Data), Author: Magnusson

About

Log in?

DTU users get better search results including licensed content and discounts on order fees.

Anyone can log in and get personalized features such as favorites, tags and feeds.

DTU Findit

Recent

title:(Leave-One-Out Cross-Validation for Bayesian Model Comparison in Large Data) Author: Magnusson

Boolean:	`(bicycle AND helmet) OR (head AND protection)` (always group AND in parenthesis)
Title:	`title:(climate change)`
Author:	`author:("bohr niels" OR "bohr n")` (avoid only full first name)
Phrase:	`"water pump control"` (does not work with wildcards)
Wildcards:	`wom?n pharm*`

More help on how to search

Flexible matching

About search syntax

Search syntax Advanced

Close advanced

By field Using AND/OR By author

Types Article Book Journal Thesis Data Other

All

Title

Year

Abstract

Journal

Author

Supervisor

ORCID

ISSN

ISBN

DOI

This tool can help you build boolean queries suitable for doing a broad search for different synonyms or spellings of each word. Start via the drop-down below or just start typing in the search field.

{{ row.typeTitle }}: ( )

Since our index often lack the full first name of people it can be difficult to correctly search by author.

Fill in the fields and let us help you build a good query:

Last name

All complete first names

ORCID

Starting year

If you need to find everything possible, consider only searching by last name.

Use "Starting year" to ignore publications out of year range.

Author: Magnusson remove

DTU

Filter results...

Interpreted as:

title:(Leave-One-Out AND Cross-Validation AND for AND Bayesian AND Model AND Comparison AND in AND Large AND Data)

Suggestions: Include records that partially match the query

Previous 1 - 2 of 2 Next

Export

10 items by relevance

1 Book chapter

Leave-One-Out Cross-Validation for Bayesian Model Comparison in Large Data

Magnusson, Måns; Andersen, Michael Riis; Jonasson, Johan; Vehtari, Aki

Proceedings of Machine Learning Research — 2020, pp. 341-350

Recently, new methods for model assessment, based on subsampling and posterior approximations, have been proposed for scaling leave-one-out cross-validation (LOO) to large datasets. Although these methods work well for estimating predictive performance for individual models, they are less powerful

Year: 2020

Language: English

More...

lec gio kpjadmnhbf

2 Preprint article

Leave-One-Out Cross-Validation for Bayesian Model Comparison in Large Data

Magnusson, Måns; Andersen, Michael Riis; Jonasson, Johan; Vehtari, Aki