{"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/linear-transformers-as-var-models-aligning","title":"Linear Transformers as VAR Models: Aligning Autoregressive Attention Mechanisms with Autoregressive Forecasting","arxiv_id":"2502.07244","date":"2025-02-11","proceeding":null,"authors":["Jiecheng Lu","Shihao Yang"],"abstract":"Autoregressive attention-based time series forecasting (TSF) has drawn increasing interest, with mechanisms like linear attention sometimes outperforming vanilla attention. However, deeper Transformer architectures frequently misalign with autoregressive objectives, obscuring the underlying VAR structure embedded within linear attention and hindering their ability to capture the data generative processes in TSF. In this work, we first show that a single linear attention layer can be interpreted as a dynamic vector autoregressive (VAR) structure. We then explain that existing multi-layer Transformers have structural mismatches with the autoregressive forecasting objective, which impair interpretability and generalization ability. To address this, we show that by rearranging the MLP, attention, and input-output flow, multi-layer linear attention can also be aligned as a VAR model. Then, we propose Structural Aligned Mixture of VAR (SAMoVAR), a linear Transformer variant that integrates interpretable dynamic VAR weights for multivariate TSF. By aligning the Transformer architecture with autoregressive objectives, SAMoVAR delivers improved performance, interpretability, and computational efficiency, comparing to SOTA TSF models.","url_abs":"https://arxiv.org/abs/2502.07244v1","url_pdf":"https://arxiv.org/pdf/2502.07244v1.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":"linear-transformers-as-var-models-aligning","repo_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"computational-efficiency","task_name":"Computational Efficiency"},{"task_slug":"time-series-forecasting","task_name":"Time Series Forecasting"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2502.07244","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.07244"}},"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/ljc-fvnr/structural-aligned-mixture-of-var","reach":null}],"summary":{"ran":7,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":"cc613e8946fad5b9","entry":"BatchedInvertibleMatrix","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc613e8946fad5b9"}},{"code_sha256_prefix":"6ef77d317ed5c58d","entry":"FixedVAR","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6ef77d317ed5c58d"}},{"code_sha256_prefix":"fa3be66911755893","entry":"LinearAttention","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa3be66911755893"}},{"code_sha256_prefix":"4af1a565eefe778f","entry":"MLP","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4af1a565eefe778f"}},{"code_sha256_prefix":"60ee36d6fa8c1c67","entry":"MultiSegmentTokenizer","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60ee36d6fa8c1c67"}},{"code_sha256_prefix":"45502bf8690c09af","entry":"RMSNorm","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"45502bf8690c09af"}},{"code_sha256_prefix":"cc0ecd2c3201fc4c","entry":"RMSNormMultiHead","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"cc0ecd2c3201fc4c"}},{"code_sha256_prefix":"af4d19e1b7122a73","entry":"Model","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.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":"af4d19e1b7122a73"}},{"code_sha256_prefix":"ce6f9d53b28653be","entry":"Transformer","repo":"ljc-fvnr/structural-aligned-mixture-of-var","repo_kind":"official","path":"models/AutoregressiveAlignment.py","file_url":"https://github.com/ljc-fvnr/structural-aligned-mixture-of-var/blob/HEAD/models/AutoregressiveAlignment.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":"ce6f9d53b28653be"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}