{"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/learning-deep-features-in-instrumental-1","title":"Learning Deep Features in Instrumental Variable Regression","arxiv_id":"2010.07154","date":"2020-10-14","proceeding":"ICLR 2021 1","authors":["Liyuan Xu","Yutian Chen","Siddarth Srinivasan","Nando de Freitas","Arnaud Doucet","Arthur Gretton"],"abstract":"Instrumental variable (IV) regression is a standard strategy for learning causal relationships between confounded treatment and outcome variables from observational data by utilizing an instrumental variable, which affects the outcome only through the treatment. In classical IV regression, learning proceeds in two stages: stage 1 performs linear regression from the instrument to the treatment; and stage 2 performs linear regression from the treatment to the outcome, conditioned on the instrument. We propose a novel method, deep feature instrumental variable regression (DFIV), to address the case where relations between instruments, treatments, and outcomes may be nonlinear. In this case, deep neural nets are trained to define informative nonlinear features on the instruments and treatments. We propose an alternating training regime for these features to ensure good end-to-end performance when composing stages 1 and 2, thus obtaining highly flexible feature maps in a computationally efficient manner. DFIV outperforms recent state-of-the-art methods on challenging IV benchmarks, including settings involving high dimensional image data. DFIV also exhibits competitive performance in off-policy policy evaluation for reinforcement learning, which can be understood as an IV regression task.","url_abs":"https://arxiv.org/abs/2010.07154v4","url_pdf":"https://arxiv.org/pdf/2010.07154v4.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":"learning-deep-features-in-instrumental-1","repo_url":"https://github.com/liyuan9988/DeepFeatureIV","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"linear-regression","method_name":"Linear Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.07154","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.07154"}},"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/liyuan9988/DeepFeatureIV","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"ran":1,"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":"5ffbe1c20671dfad","entry":"linear_reg_pred","repo":"liyuan9988/DeepFeatureIV","repo_kind":"official","path":"src/utils/pytorch_linear_reg_utils.py","file_url":"https://github.com/liyuan9988/DeepFeatureIV/blob/HEAD/src/utils/pytorch_linear_reg_utils.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5ffbe1c20671dfad"}},{"code_sha256_prefix":"a5ec1af668c96a48","entry":"fit_linear","repo":"liyuan9988/DeepFeatureIV","repo_kind":"official","path":"src/utils/pytorch_linear_reg_utils.py","file_url":"https://github.com/liyuan9988/DeepFeatureIV/blob/HEAD/src/utils/pytorch_linear_reg_utils.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":"a5ec1af668c96a48"}},{"code_sha256_prefix":"815453ea8ff9e761","entry":"linear_reg_loss","repo":"liyuan9988/DeepFeatureIV","repo_kind":"official","path":"src/utils/pytorch_linear_reg_utils.py","file_url":"https://github.com/liyuan9988/DeepFeatureIV/blob/HEAD/src/utils/pytorch_linear_reg_utils.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":"815453ea8ff9e761"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}