{"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/latent-sdes-on-homogeneous-spaces-1","title":"Latent SDEs on Homogeneous Spaces","arxiv_id":"2306.16248","date":"2023-06-28","proceeding":"NeurIPS 2023 11","authors":["Sebastian Zeng","Florian Graf","Roland Kwitt"],"abstract":"We consider the problem of variational Bayesian inference in a latent variable model where a (possibly complex) observed stochastic process is governed by the solution of a latent stochastic differential equation (SDE). Motivated by the challenges that arise when trying to learn an (almost arbitrary) latent neural SDE from data, such as efficient gradient computation, we take a step back and study a specific subclass instead. In our case, the SDE evolves on a homogeneous latent space and is induced by stochastic dynamics of the corresponding (matrix) Lie group. In learning problems, SDEs on the unit n-sphere are arguably the most relevant incarnation of this setup. Notably, for variational inference, the sphere not only facilitates using a truly uninformative prior, but we also obtain a particularly simple and intuitive expression for the Kullback-Leibler divergence between the approximate posterior and prior process in the evidence lower bound. Experiments demonstrate that a latent SDE of the proposed type can be learned efficiently by means of an existing one-step geometric Euler-Maruyama scheme. Despite restricting ourselves to a less rich class of SDEs, we achieve competitive or even state-of-the-art results on various time series interpolation/classification problems.","url_abs":"https://arxiv.org/abs/2306.16248v3","url_pdf":"https://arxiv.org/pdf/2306.16248v3.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":"latent-sdes-on-homogeneous-spaces-1","repo_url":"https://github.com/plus-rkwitt/latentsdeonhs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"bayesian-inference","task_name":"Bayesian Inference"},{"task_slug":"variational-inference","task_name":"Variational Inference"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.16248","atlas_url":"https://app.syntology.ai/?focus=2306.16248","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.16248"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/plus-rkwitt/latentsdeonhs","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"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":"75a1b0d78086afa8","entry":"compute_accuracy","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"activity_classification.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/activity_classification.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"75a1b0d78086afa8"}},{"code_sha256_prefix":"a0b5a9a4be5b403e","entry":"evaluate","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"activity_classification.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/activity_classification.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a0b5a9a4be5b403e"}},{"code_sha256_prefix":"419c28179ba1d796","entry":"evaluate","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"pendulum_regression.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/pendulum_regression.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"419c28179ba1d796"}},{"code_sha256_prefix":"e31148ff0fa79c2a","entry":"evaluate","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"rotating_mnist.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/rotating_mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e31148ff0fa79c2a"}},{"code_sha256_prefix":"5554eb5b1338d31f","entry":"extend_argparse","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"physionet_interpolation.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/physionet_interpolation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5554eb5b1338d31f"}},{"code_sha256_prefix":"bb7e1201fae20d56","entry":"extend_argparse","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"activity_classification.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/activity_classification.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bb7e1201fae20d56"}},{"code_sha256_prefix":"f1494f5a87cb16ab","entry":"extend_argparse","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"pendulum_interpolation.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/pendulum_interpolation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1494f5a87cb16ab"}},{"code_sha256_prefix":"10d0b2d599c1d47b","entry":"extend_argparse","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"rotating_mnist.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/rotating_mnist.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"10d0b2d599c1d47b"}},{"code_sha256_prefix":"fb4c951120fc2606","entry":"generic_train","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"core/training.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/core/training.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fb4c951120fc2606"}},{"code_sha256_prefix":"6c93241504bf28d8","entry":"set_up_logging","repo":"plus-rkwitt/latentsdeonhs","repo_kind":"official","path":"utils/logger.py","file_url":"https://github.com/plus-rkwitt/latentsdeonhs/blob/HEAD/utils/logger.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6c93241504bf28d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}