{"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/an-adaptive-tangent-feature-perspective-of","title":"An Adaptive Tangent Feature Perspective of Neural Networks","arxiv_id":"2308.15478","date":"2023-08-29","proceeding":null,"authors":["Daniel LeJeune","Sina AlEMohammad"],"abstract":"In order to better understand feature learning in neural networks, we propose a framework for understanding linear models in tangent feature space where the features are allowed to be transformed during training. We consider linear transformations of features, resulting in a joint optimization over parameters and transformations with a bilinear interpolation constraint. We show that this optimization problem has an equivalent linearly constrained optimization with structured regularization that encourages approximately low rank solutions. Specializing to neural network structure, we gain insights into how the features and thus the kernel function change, providing additional nuance to the phenomenon of kernel alignment when the target function is poorly represented using tangent features. We verify our theoretical observations in the kernel alignment of real neural networks.","url_abs":"https://arxiv.org/abs/2308.15478v3","url_pdf":"https://arxiv.org/pdf/2308.15478v3.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":"an-adaptive-tangent-feature-perspective-of","repo_url":"https://github.com/dlej/adaptive-feature-perspective","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2308.15478","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15478"}},"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/dlej/adaptive-feature-perspective","reach":null}],"summary":{"ran_draft_wrong":2,"unverified":1},"by_repo_kind":{"official":{"samples":3,"ran":2,"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":"04eea3d38f935226","entry":"format_timedelta","repo":"dlej/adaptive-feature-perspective","repo_kind":"official","path":"batch_gpu.py","file_url":"https://github.com/dlej/adaptive-feature-perspective/blob/HEAD/batch_gpu.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"04eea3d38f935226"}},{"code_sha256_prefix":"eb1881960e15d93e","entry":"load_experiments_from_json","repo":"dlej/adaptive-feature-perspective","repo_kind":"official","path":"batch_gpu.py","file_url":"https://github.com/dlej/adaptive-feature-perspective/blob/HEAD/batch_gpu.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"eb1881960e15d93e"}},{"code_sha256_prefix":"48e54303d2ca26ec","entry":"run_experiment","repo":"dlej/adaptive-feature-perspective","repo_kind":"official","path":"batch_gpu.py","file_url":"https://github.com/dlej/adaptive-feature-perspective/blob/HEAD/batch_gpu.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"48e54303d2ca26ec"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}