@article{
 title = {Structured Inference Networks for Nonlinear State Space Models},
 type = {article},
 id = {10b7ed7d-a5c8-35c5-9125-ea85d6c71a9f},
 created = {2018-02-14T12:53:37.892Z},
 file_attached = {true},
 profile_id = {ea20c45e-0866-3373-a162-5a7398e4ac0b},
 group_id = {2d721da3-627a-3ca3-862a-cd2d130d920f},
 last_modified = {2018-02-14T12:53:39.759Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {false},
 hidden = {false},
 folder_uuids = {d1061552-d7f6-480b-a466-74128dc5a51f},
 private_publication = {false},
 abstract = {Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and tran-sition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.},
 bibtype = {article},
 author = {Krishnan, Rahul G and Shalit, Uri and Sontag, David}
}

{"_id":"BjEuH4riyfNEm8vry","bibbaseid":"krishnan-shalit-sontag-structuredinferencenetworksfornonlinearstatespacemodels","downloads":0,"creationDate":"2018-10-05T13:09:54.312Z","title":"Structured Inference Networks for Nonlinear State Space Models","author_short":["Krishnan, R., G.","Shalit, U.","Sontag, D."],"year":null,"bibtype":"article","biburl":null,"bibdata":{"title":"Structured Inference Networks for Nonlinear State Space Models","type":"article","id":"10b7ed7d-a5c8-35c5-9125-ea85d6c71a9f","created":"2018-02-14T12:53:37.892Z","file_attached":"true","profile_id":"ea20c45e-0866-3373-a162-5a7398e4ac0b","group_id":"2d721da3-627a-3ca3-862a-cd2d130d920f","last_modified":"2018-02-14T12:53:39.759Z","read":false,"starred":false,"authored":false,"confirmed":false,"hidden":false,"folder_uuids":"d1061552-d7f6-480b-a466-74128dc5a51f","private_publication":false,"abstract":"Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and tran-sition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.","bibtype":"article","author":"Krishnan, Rahul G and Shalit, Uri and Sontag, David","bibtex":"@article{\n title = {Structured Inference Networks for Nonlinear State Space Models},\n type = {article},\n id = {10b7ed7d-a5c8-35c5-9125-ea85d6c71a9f},\n created = {2018-02-14T12:53:37.892Z},\n file_attached = {true},\n profile_id = {ea20c45e-0866-3373-a162-5a7398e4ac0b},\n group_id = {2d721da3-627a-3ca3-862a-cd2d130d920f},\n last_modified = {2018-02-14T12:53:39.759Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {false},\n hidden = {false},\n folder_uuids = {d1061552-d7f6-480b-a466-74128dc5a51f},\n private_publication = {false},\n abstract = {Gaussian state space models have been used for decades as generative models of sequential data. They admit an intuitive probabilistic interpretation, have a simple functional form, and enjoy widespread adoption. We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and tran-sition distributions are modeled by deep neural networks. Our learning algorithm simultaneously learns a compiled inference network and the generative model, leveraging a structured variational approximation parameterized by recurrent neural networks to mimic the posterior distribution. We apply the learning algorithm to both synthetic and real-world datasets, demonstrating its scalability and versatility. We find that using the structured approximation to the posterior results in models with significantly higher held-out likelihood.},\n bibtype = {article},\n author = {Krishnan, Rahul G and Shalit, Uri and Sontag, David}\n}","author_short":["Krishnan, R., G.","Shalit, U.","Sontag, D."],"urls":{"Paper":"https://bibbase.org/service/mendeley/b14f907e-b397-3956-8196-166e91ca3313/file/3c8219e6-fbbb-cc57-7a89-7e1c48110976/Structured_Inference_Networks_for_Nonlinear_State_Space_Models.pdf.pdf"},"bibbaseid":"krishnan-shalit-sontag-structuredinferencenetworksfornonlinearstatespacemodels","role":"author","downloads":0},"search_terms":["structured","inference","networks","nonlinear","state","space","models","krishnan","shalit","sontag"],"keywords":[],"authorIDs":[]}