{"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/structured-linear-cdes-maximally-expressive","title":"Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models","arxiv_id":"2505.17761","date":"2025-05-23","proceeding":null,"authors":["Benjamin Walker","Lingyi Yang","Nicola Muca Cirone","Cristopher Salvi","Terry Lyons"],"abstract":"Structured Linear Controlled Differential Equations (SLiCEs) provide a unifying framework for sequence models with structured, input-dependent state-transition matrices that retain the maximal expressivity of dense matrices whilst being cheaper to compute. The framework encompasses existing architectures, such as input-dependent block-diagonal linear recurrent neural networks and DeltaNet's diagonal-plus-low-rank structure, as well as two novel variants based on sparsity and the Walsh--Hadamard transform. We prove that, unlike the diagonal state-transition matrices of S4 and Mamba, SLiCEs employing block-diagonal, sparse, or Walsh--Hadamard matrices match the maximal expressivity of dense matrices. Empirically, SLiCEs solve the $A_5$ state-tracking benchmark with a single layer, achieve best-in-class length generalisation on regular language tasks among parallel-in-time models, and match the state-of-the-art performance of log neural controlled differential equations on six multivariate time-series classification datasets while cutting the average time per training step by a factor of twenty.","url_abs":"https://arxiv.org/abs/2505.17761v1","url_pdf":"https://arxiv.org/pdf/2505.17761v1.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":"structured-linear-cdes-maximally-expressive","repo_url":"https://github.com/benjamin-walker/log-neural-cdes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"structured-linear-cdes-maximally-expressive","repo_url":"https://github.com/benjamin-walker/structured-linear-cdes","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"}],"methods":[{"method_slug":"mamba","method_name":"Mamba"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.17761","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.17761"}},"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/benjamin-walker/log-neural-cdes","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/benjamin-walker/structured-linear-cdes","reach":null}],"summary":{"ran_honours":3},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":2}},"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":"43bc67dcbc9b1030","entry":"depth","repo":"benjamin-walker/log-neural-cdes","repo_kind":"official","path":"models/LinearNeuralCDEs.py","file_url":"https://github.com/benjamin-walker/log-neural-cdes/blob/HEAD/models/LinearNeuralCDEs.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43bc67dcbc9b1030"}},{"code_sha256_prefix":"452a96ba0f01db31","entry":"hadamard_matrix","repo":"benjamin-walker/structured-linear-cdes","repo_kind":"official","path":"models/slcde.py","file_url":"https://github.com/benjamin-walker/structured-linear-cdes/blob/HEAD/models/slcde.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"452a96ba0f01db31"}},{"code_sha256_prefix":"44c918b1c6d022f5","entry":"to_tuple","repo":"benjamin-walker/log-neural-cdes","repo_kind":"official","path":"models/LinearNeuralCDEs.py","file_url":"https://github.com/benjamin-walker/log-neural-cdes/blob/HEAD/models/LinearNeuralCDEs.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"44c918b1c6d022f5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}