Orthogonal Approximation of Marginal Likelihood of Generative Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F19%3A00522204" target="_blank" >RIV/67985556:_____/19:00522204 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/19:00339857

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Orthogonal Approximation of Marginal Likelihood of Generative Models

Popis výsledku v původním jazyce

This paper presents a new approximation of the marginal likelihood of generative models which is used as a score for anomaly detection. The score is motivated by the shortcoming of the popular reconstruction error that it can behave arbitrarily outside the known samples. The proposed score corrects this by orthogonal combination of the reconstruction error and the likelihood in the latent space. As experimentally shown on benchmark problems from anomaly detection and illustrated on a toy problem, this combination lends the score robustness to outliers. Generative models evaluated with this score outperformed the competing methods especially in tasks of learning distribution from data corrupted by anomalies. Finally, the score is compatible with contemporary generative models, namely variational auto-encoders and generative adversarial networks

Název v anglickém jazyce

Orthogonal Approximation of Marginal Likelihood of Generative Models

Popis výsledku anglicky

This paper presents a new approximation of the marginal likelihood of generative models which is used as a score for anomaly detection. The score is motivated by the shortcoming of the popular reconstruction error that it can behave arbitrarily outside the known samples. The proposed score corrects this by orthogonal combination of the reconstruction error and the likelihood in the latent space. As experimentally shown on benchmark problems from anomaly detection and illustrated on a toy problem, this combination lends the score robustness to outliers. Generative models evaluated with this score outperformed the competing methods especially in tasks of learning distribution from data corrupted by anomalies. Finally, the score is compatible with contemporary generative models, namely variational auto-encoders and generative adversarial networks

Druh

O - Ostatní výsledky

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů