Hyperspherical Variational Auto-Encoders. Davidson, T., R., Falorsi, L., De Cao, N., Kipf, T., & Tomczak, J., M. arXiv:1804.00891 [cs, stat], 9, 2018. ![Hyperspherical Variational Auto-Encoders [link]](https://bibbase.org/img/filetypes/link.svg "link")
Website abstract bibtex The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or \$\textbackslashmathcal\S\\$-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, \$\textbackslashmathcal\N\\$-VAE, in low dimensions on other data types.
@article{
title = {Hyperspherical Variational Auto-Encoders},
type = {article},
year = {2018},
keywords = {Computer Science - Machine Learning,Statistics - Machine Learning},
websites = {http://arxiv.org/abs/1804.00891},
month = {9},
id = {80a3859e-084c-318b-8598-fbaedd606332},
created = {2022-03-28T09:45:03.638Z},
accessed = {2022-03-26},
file_attached = {true},
profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},
group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},
last_modified = {2022-03-29T08:05:33.433Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
citation_key = {davidsonHypersphericalVariationalAutoEncoders2018},
source_type = {article},
notes = {arXiv: 1804.00891},
private_publication = {false},
abstract = {The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or \$\textbackslashmathcal\S\\$-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, \$\textbackslashmathcal\N\\$-VAE, in low dimensions on other data types.},
bibtype = {article},
author = {Davidson, Tim R and Falorsi, Luca and De Cao, Nicola and Kipf, Thomas and Tomczak, Jakub M},
journal = {arXiv:1804.00891 [cs, stat]}
}
Downloads: 0
{"_id":"8FcmD77jK375WTH5v","bibbaseid":"davidson-falorsi-decao-kipf-tomczak-hypersphericalvariationalautoencoders-2018","author_short":["Davidson, T., R.","Falorsi, L.","De Cao, N.","Kipf, T.","Tomczak, J., M."],"bibdata":{"title":"Hyperspherical Variational Auto-Encoders","type":"article","year":"2018","keywords":"Computer Science - Machine Learning,Statistics - Machine Learning","websites":"http://arxiv.org/abs/1804.00891","month":"9","id":"80a3859e-084c-318b-8598-fbaedd606332","created":"2022-03-28T09:45:03.638Z","accessed":"2022-03-26","file_attached":"true","profile_id":"235249c2-3ed4-314a-b309-b1ea0330f5d9","group_id":"1ff583c0-be37-34fa-9c04-73c69437d354","last_modified":"2022-03-29T08:05:33.433Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"citation_key":"davidsonHypersphericalVariationalAutoEncoders2018","source_type":"article","notes":"arXiv: 1804.00891","private_publication":false,"abstract":"The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or \\$\\textbackslashmathcal\\S\\\\$-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, \\$\\textbackslashmathcal\\N\\\\$-VAE, in low dimensions on other data types.","bibtype":"article","author":"Davidson, Tim R and Falorsi, Luca and De Cao, Nicola and Kipf, Thomas and Tomczak, Jakub M","journal":"arXiv:1804.00891 [cs, stat]","bibtex":"@article{\n title = {Hyperspherical Variational Auto-Encoders},\n type = {article},\n year = {2018},\n keywords = {Computer Science - Machine Learning,Statistics - Machine Learning},\n websites = {http://arxiv.org/abs/1804.00891},\n month = {9},\n id = {80a3859e-084c-318b-8598-fbaedd606332},\n created = {2022-03-28T09:45:03.638Z},\n accessed = {2022-03-26},\n file_attached = {true},\n profile_id = {235249c2-3ed4-314a-b309-b1ea0330f5d9},\n group_id = {1ff583c0-be37-34fa-9c04-73c69437d354},\n last_modified = {2022-03-29T08:05:33.433Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n citation_key = {davidsonHypersphericalVariationalAutoEncoders2018},\n source_type = {article},\n notes = {arXiv: 1804.00891},\n private_publication = {false},\n abstract = {The Variational Auto-Encoder (VAE) is one of the most used unsupervised machine learning models. But although the default choice of a Gaussian distribution for both the prior and posterior represents a mathematically convenient distribution often leading to competitive results, we show that this parameterization fails to model data with a latent hyperspherical structure. To address this issue we propose using a von Mises-Fisher (vMF) distribution instead, leading to a hyperspherical latent space. Through a series of experiments we show how such a hyperspherical VAE, or \\$\\textbackslashmathcal\\S\\\\$-VAE, is more suitable for capturing data with a hyperspherical latent structure, while outperforming a normal, \\$\\textbackslashmathcal\\N\\\\$-VAE, in low dimensions on other data types.},\n bibtype = {article},\n author = {Davidson, Tim R and Falorsi, Luca and De Cao, Nicola and Kipf, Thomas and Tomczak, Jakub M},\n journal = {arXiv:1804.00891 [cs, stat]}\n}","author_short":["Davidson, T., R.","Falorsi, L.","De Cao, N.","Kipf, T.","Tomczak, J., M."],"urls":{"Website":"http://arxiv.org/abs/1804.00891"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"davidson-falorsi-decao-kipf-tomczak-hypersphericalvariationalautoencoders-2018","role":"author","keyword":["Computer Science - Machine Learning","Statistics - Machine Learning"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["6yqkfgG5XRop3rtQ6","ya2CyA73rpZseyrZ8","2252seNhipfTmjEBQ"],"keywords":["computer science - machine learning","statistics - machine learning"],"search_terms":["hyperspherical","variational","auto","encoders","davidson","falorsi","de cao","kipf","tomczak"],"title":"Hyperspherical Variational Auto-Encoders","year":2018}