{"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/deep-latent-state-space-models-for-time","title":"Deep Latent State Space Models for Time-Series Generation","arxiv_id":"2212.12749","date":"2022-12-24","proceeding":null,"authors":["Linqi Zhou","Michael Poli","Winnie Xu","Stefano Massaroli","Stefano Ermon"],"abstract":"Methods based on ordinary differential equations (ODEs) are widely used to build generative models of time-series. In addition to high computational overhead due to explicitly computing hidden states recurrence, existing ODE-based models fall short in learning sequence data with sharp transitions - common in many real-world systems - due to numerical challenges during optimization. In this work, we propose LS4, a generative model for sequences with latent variables evolving according to a state space ODE to increase modeling capacity. Inspired by recent deep state space models (S4), we achieve speedups by leveraging a convolutional representation of LS4 which bypasses the explicit evaluation of hidden states. We show that LS4 significantly outperforms previous continuous-time generative models in terms of marginal distribution, classification, and prediction scores on real-world datasets in the Monash Forecasting Repository, and is capable of modeling highly stochastic data with sharp temporal transitions. LS4 sets state-of-the-art for continuous-time latent generative models, with significant improvement of mean squared error and tighter variational lower bounds on irregularly-sampled datasets, while also being x100 faster than other baselines on long sequences.","url_abs":"https://arxiv.org/abs/2212.12749v3","url_pdf":"https://arxiv.org/pdf/2212.12749v3.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":"deep-latent-state-space-models-for-time","repo_url":"https://github.com/alexzhou907/ls4","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"state-space-models","task_name":"State Space Models"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-generation","task_name":"Time Series Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2212.12749","atlas_url":"https://app.syntology.ai/?focus=2212.12749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2212.12749"}},"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/alexzhou907/ls4","reach":null}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":"9d3689d8de6ef9b4","entry":"binary_ce_loss","repo":"alexzhou907/ls4","repo_kind":"official","path":"models/ls4.py","file_url":"https://github.com/alexzhou907/ls4/blob/HEAD/models/ls4.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9d3689d8de6ef9b4"}},{"code_sha256_prefix":"ae3fee05e3584b35","entry":"multiclass_ce_loss","repo":"alexzhou907/ls4","repo_kind":"official","path":"models/ls4.py","file_url":"https://github.com/alexzhou907/ls4/blob/HEAD/models/ls4.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ae3fee05e3584b35"}},{"code_sha256_prefix":"aab83273893c15bf","entry":"setup_optimizer","repo":"alexzhou907/ls4","repo_kind":"official","path":"train_monash.py","file_url":"https://github.com/alexzhou907/ls4/blob/HEAD/train_monash.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aab83273893c15bf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}