{"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/universal-approximation-with-softmax","title":"Universal Approximation with Softmax Attention","arxiv_id":"2504.15956","date":"2025-04-22","proceeding":null,"authors":["Jerry Yao-Chieh Hu","Hude Liu","Hong-Yu Chen","Weimin Wu","Han Liu"],"abstract":"We prove that with linear transformations, both (i) two-layer self-attention and (ii) one-layer self-attention followed by a softmax function are universal approximators for continuous sequence-to-sequence functions on compact domains. Our main technique is a new interpolation-based method for analyzing attention's internal mechanism. This leads to our key insight: self-attention is able to approximate a generalized version of ReLU to arbitrary precision, and hence subsumes many known universal approximators. Building on these, we show that two-layer multi-head attention alone suffices as a sequence-to-sequence universal approximator. In contrast, prior works rely on feed-forward networks to establish universal approximation in Transformers. Furthermore, we extend our techniques to show that, (softmax-)attention-only layers are capable of approximating various statistical models in-context. We believe these techniques hold independent interest.","url_abs":"https://arxiv.org/abs/2504.15956v1","url_pdf":"https://arxiv.org/pdf/2504.15956v1.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":"universal-approximation-with-softmax","repo_url":"https://github.com/magics-lab/uap_attention","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.15956","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.15956"}},"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/magics-lab/uap_attention","reach":null}],"summary":{"ran":3},"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":3,"samples":[{"code_sha256_prefix":"ce2f846fdbc8bf4b","entry":"ExtendedMappingA","repo":"magics-lab/uap_attention","repo_kind":"official","path":"attn_map.py","file_url":"https://github.com/magics-lab/uap_attention/blob/HEAD/attn_map.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ce2f846fdbc8bf4b"}},{"code_sha256_prefix":"10cde310c3cbf4e6","entry":"OneLayerAttentionModelExtendedManualKV","repo":"magics-lab/uap_attention","repo_kind":"official","path":"attn_map.py","file_url":"https://github.com/magics-lab/uap_attention/blob/HEAD/attn_map.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"10cde310c3cbf4e6"}},{"code_sha256_prefix":"309e3ba1710bc97a","entry":"SingleHeadAttentionLayerWithManualKeyValue","repo":"magics-lab/uap_attention","repo_kind":"official","path":"attn_map.py","file_url":"https://github.com/magics-lab/uap_attention/blob/HEAD/attn_map.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"309e3ba1710bc97a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}