Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/20.500.14279/10037
Τίτλος: | Asymmetric deep generative models | Συγγραφείς: | Partaourides, Charalampos Chatzis, Sotirios P. |
Major Field of Science: | Engineering and Technology | Field Category: | Electrical Engineering - Electronic Engineering - Information Engineering | Λέξεις-κλειδιά: | Deep generative model;Restricted multivariate skew-Normal distribution;Semi-supervised learning;Variational inference | Ημερομηνία Έκδοσης: | 7-Ιου-2017 | Πηγή: | Neurocomputing, 2017, vol. 241, pp. 90-96 | Volume: | 241 | Start page: | 90 | End page: | 96 | Περιοδικό: | Neurocomputing | Περίληψη: | Amortized variational inference, whereby the inferred latent variable posterior distributions are parameterized by means of neural network functions, has invigorated a new wave of innovation in the field of generative latent variable modeling, giving rise to the family of deep generative models (DGMs). Existing DGM formulations are based on the assumption of a symmetric Gaussian posterior over the model latent variables. This assumption, although mathematically convenient, can be well-expected to undermine the eventually obtained representation power, as it imposes apparent expressiveness limitations. Indeed, it has been recently shown that even some moderate increase in the latent variable posterior expressiveness, obtained by introducing an additional level of dependencies upon auxiliary (Gaussian) latent variables, can result in significant performance improvements in the context of semi-supervised learning tasks. Inspired from these advances, in this paper we examine whether a more potent increase in the expressiveness and representation power of modern DGMs can be achieved by completely relaxing their typical symmetric (Gaussian) latent variable posterior assumptions: Specifically, we consider DGMs with asymmetric posteriors, formulated as restricted multivariate skew-Normal (rMSN) distributions. We derive an efficient amortized variational inference algorithm for the proposed model, and exhibit its superiority over the current state-of-the-art in several semi-supervised learning benchmarks. | URI: | https://hdl.handle.net/20.500.14279/10037 | ISSN: | 09252312 | DOI: | 10.1016/j.neucom.2017.02.028 | Rights: | © Elsevier | Type: | Article | Affiliation: | Cyprus University of Technology |
Εμφανίζεται στις συλλογές: | Άρθρα/Articles |
CORE Recommender
SCOPUSTM
Citations
13
checked on 9 Νοε 2023
WEB OF SCIENCETM
Citations
9
Last Week
0
0
Last month
0
0
checked on 29 Οκτ 2023
Page view(s)
447
Last Week
3
3
Last month
11
11
checked on 12 Μαϊ 2024
Google ScholarTM
Check
Altmetric
Όλα τα τεκμήρια του δικτυακού τόπου προστατεύονται από πνευματικά δικαιώματα