Yes, but did it work?: Evaluating variational inference

Yuling Yao; Aki Vehtari; Daniel Simpson; Andrew Gelman

Yes, but did it work? Evaluating variational inference

Yuling Yao^*, Aki Vehtari, Daniel Simpson, Andrew Gelman

^*Tämän työn vastaava kirjoittaja

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

7 Sitaatiot (Scopus)

30 Lataukset (Pure)

Abstrakti

While it's always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation". We propose two diagnostic algorithms to alleviate this problem. The Paretosmoothed importance sampling (PSIS) diagnostic gives a goodness of fit measurement for joint distributions, while simultaneously improving the error in the estimate. The variational simulationbased calibration (VSBC) assesses the average performance of point estimates.

Alkuperäiskieli	Englanti
Otsikko	35th International Conference on Machine Learning, ICML 2018
Toimittajat	Jennifer Dy, Andreas Krause
Sivut	8887-8895
Sivumäärä	9
Vuosikerta	12
ISBN (elektroninen)	9781510867963
Tila	Julkaistu - 1 tammikuuta 2018
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisuussa
Tapahtuma	INTERNATIONAL CONFERENCE ON MACHINE LEARNING - Stockholm, Ruotsi Kesto: 10 heinäkuuta 2018 → 15 heinäkuuta 2018 Konferenssinumero: 35

Julkaisusarja

Nimi	Proceedings of Machine Learning Research
Kustantaja	PMLR
Numero	80
ISSN (elektroninen)	1938-7228

Conference

Conference	INTERNATIONAL CONFERENCE ON MACHINE LEARNING
Lyhennettä	ICML
Maa	Ruotsi
Kaupunki	Stockholm
Ajanjakso	10/07/2018 → 15/07/2018

Pääsy asiakirjaan

yao18aFinal published version, 642 KB

Sormenjälki Sukella tutkimusaiheisiin 'Yes, but did it work? Evaluating variational inference'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä

@inproceedings{cda14f546e814974af57e1a87ed1f532,

title = "Yes, but did it work?: Evaluating variational inference",

abstract = "While it's always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation{"}. We propose two diagnostic algorithms to alleviate this problem. The Paretosmoothed importance sampling (PSIS) diagnostic gives a goodness of fit measurement for joint distributions, while simultaneously improving the error in the estimate. The variational simulationbased calibration (VSBC) assesses the average performance of point estimates.",

author = "Yuling Yao and Aki Vehtari and Daniel Simpson and Andrew Gelman",

year = "2018",

month = jan,

day = "1",

language = "English",

volume = "12",

series = "Proceedings of Machine Learning Research",

publisher = "PMLR",

number = "80",

pages = "8887--8895",

editor = "Jennifer Dy and Andreas Krause",

booktitle = "35th International Conference on Machine Learning, ICML 2018",

note = "International Conference on Machine Learning, ICML ; Conference date: 10-07-2018 Through 15-07-2018",

}

Yao, Y, Vehtari, A, Simpson, D & Gelman, A 2018, Yes, but did it work? Evaluating variational inference. julkaisussa J Dy & A Krause (toim), 35th International Conference on Machine Learning, ICML 2018. Vuosikerta 12, Proceedings of Machine Learning Research, Nro 80, Sivut 8887-8895, INTERNATIONAL CONFERENCE ON MACHINE LEARNING, Stockholm, Ruotsi, 10/07/2018. <http://proceedings.mlr.press/v80/yao18a.html>

Yes, but did it work? Evaluating variational inference. / Yao, Yuling; Vehtari, Aki; Simpson, Daniel; Gelman, Andrew.

35th International Conference on Machine Learning, ICML 2018. toim. / Jennifer Dy; Andreas Krause. Vuosikerta 12 2018. s. 8887-8895 (Proceedings of Machine Learning Research; Nro 80).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference contribution › Scientific › vertaisarvioitu

TY - GEN

T1 - Yes, but did it work?

T2 - International Conference on Machine Learning

AU - Yao, Yuling

AU - Vehtari, Aki

AU - Simpson, Daniel

AU - Gelman, Andrew

N1 - Conference code: 35

PY - 2018/1/1

Y1 - 2018/1/1

N2 - While it's always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation". We propose two diagnostic algorithms to alleviate this problem. The Paretosmoothed importance sampling (PSIS) diagnostic gives a goodness of fit measurement for joint distributions, while simultaneously improving the error in the estimate. The variational simulationbased calibration (VSBC) assesses the average performance of point estimates.

AB - While it's always possible to compute a variational approximation to a posterior distribution, it can be difficult to discover problems with this approximation". We propose two diagnostic algorithms to alleviate this problem. The Paretosmoothed importance sampling (PSIS) diagnostic gives a goodness of fit measurement for joint distributions, while simultaneously improving the error in the estimate. The variational simulationbased calibration (VSBC) assesses the average performance of point estimates.

UR - http://www.scopus.com/inward/record.url?scp=85057318872&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85057318872

VL - 12

T3 - Proceedings of Machine Learning Research

SP - 8887

EP - 8895

BT - 35th International Conference on Machine Learning, ICML 2018

A2 - Dy, Jennifer

A2 - Krause, Andreas

Y2 - 10 July 2018 through 15 July 2018

ER -