Loss functions

Robert C. Williamson

doi:10.1007/978-3-642-41136-6_8

Loss functions

Robert C. Williamson^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Chapter › peer-review

4 Citations (Scopus)

Abstract

Vapnik described the “three main learning problems” of pattern recognition, regression estimation and density estimation. These are defined in terms of the loss functions used to evaluate performance (0-1 loss, squared loss, and log loss, respectively). But there are many other loss functions one could use. In this chapter I will summarise some recent work by me and colleagues studying the theoretical aspects of loss functions. The results elucidate the richness of the set of loss functions and explain some of the implications of their choice.

Original language	English
Title of host publication	Empirical Inference
Subtitle of host publication	Festschrift in Honor of Vladimir N. Vapnik
Publisher	Springer Berlin
Pages	71-80
Number of pages	10
ISBN (Electronic)	9783642411366
ISBN (Print)	9783642411359
DOIs	https://doi.org/10.1007/978-3-642-41136-6_8
Publication status	Published - 1 Jan 2013

Access to Document

10.1007/978-3-642-41136-6_8

Cite this

@inbook{830440f8093f4c22a18c54ae82252e59,

title = "Loss functions",

abstract = "Vapnik described the “three main learning problems” of pattern recognition, regression estimation and density estimation. These are defined in terms of the loss functions used to evaluate performance (0-1 loss, squared loss, and log loss, respectively). But there are many other loss functions one could use. In this chapter I will summarise some recent work by me and colleagues studying the theoretical aspects of loss functions. The results elucidate the richness of the set of loss functions and explain some of the implications of their choice.",

author = "Williamson, \{Robert C.\}",

note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2013.",

year = "2013",

month = jan,

day = "1",

doi = "10.1007/978-3-642-41136-6\_8",

language = "English",

isbn = "9783642411359",

pages = "71--80",

booktitle = "Empirical Inference",

publisher = "Springer Berlin",

address = "Germany",

}

TY - CHAP

T1 - Loss functions

AU - Williamson, Robert C.

PY - 2013/1/1

Y1 - 2013/1/1

N2 - Vapnik described the “three main learning problems” of pattern recognition, regression estimation and density estimation. These are defined in terms of the loss functions used to evaluate performance (0-1 loss, squared loss, and log loss, respectively). But there are many other loss functions one could use. In this chapter I will summarise some recent work by me and colleagues studying the theoretical aspects of loss functions. The results elucidate the richness of the set of loss functions and explain some of the implications of their choice.

AB - Vapnik described the “three main learning problems” of pattern recognition, regression estimation and density estimation. These are defined in terms of the loss functions used to evaluate performance (0-1 loss, squared loss, and log loss, respectively). But there are many other loss functions one could use. In this chapter I will summarise some recent work by me and colleagues studying the theoretical aspects of loss functions. The results elucidate the richness of the set of loss functions and explain some of the implications of their choice.

UR - https://www.scopus.com/pages/publications/84939622844

U2 - 10.1007/978-3-642-41136-6_8

DO - 10.1007/978-3-642-41136-6_8

M3 - Chapter

SN - 9783642411359

SP - 71

EP - 80

BT - Empirical Inference

PB - Springer Berlin

ER -

Loss functions

Abstract

Access to Document

Other files and links

Fingerprint

Cite this