{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/gaussian-process-prior-variational","title":"Gaussian Process Prior Variational Autoencoders","arxiv_id":"1810.11738","date":"2018-10-28","proceeding":"NeurIPS 2018 12","authors":["Francesco Paolo Casale","Adrian V. Dalca","Luca Saglietti","Jennifer Listgarten","Nicolo Fusi"],"abstract":"Variational autoencoders (VAE) are a powerful and widely-used class of models\nto learn complex data distributions in an unsupervised fashion. One important\nlimitation of VAEs is the prior assumption that latent sample representations\nare independent and identically distributed. However, for many important\ndatasets, such as time-series of images, this assumption is too strong:\naccounting for covariances between samples, such as those in time, can yield to\na more appropriate model specification and improve performance in downstream\ntasks. In this work, we introduce a new model, the Gaussian Process (GP) Prior\nVariational Autoencoder (GPPVAE), to specifically address this issue. The\nGPPVAE aims to combine the power of VAEs with the ability to model correlations\nafforded by GP priors. To achieve efficient inference in this new class of\nmodels, we leverage structure in the covariance matrix, and introduce a new\nstochastic backpropagation strategy that allows for computing stochastic\ngradients in a distributed and low-memory fashion. We show that our method\noutperforms conditional VAEs (CVAEs) and an adaptation of standard VAEs in two\nimage data applications.","url_abs":"http://arxiv.org/abs/1810.11738v2","url_pdf":"http://arxiv.org/pdf/1810.11738v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"gaussian-process-prior-variational","repo_url":"https://github.com/fpcasale/GPPVAE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"gaussian-process-prior-variational","repo_url":"https://github.com/ratschlab/SVGP-VAE","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"gaussian-process-prior-variational","repo_url":"https://github.com/shixinxing/nngpvae-official","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.11738","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.11738"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shixinxing/nngpvae-official","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fpcasale/GPPVAE","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ratschlab/SVGP-VAE","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9df13e595576ff5e","entry":"eval_step","repo":"fpcasale/GPPVAE","repo_kind":"official","path":"pysrc/faceplace/train_gppvae.py","file_url":"https://github.com/fpcasale/GPPVAE/blob/HEAD/pysrc/faceplace/train_gppvae.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9df13e595576ff5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}