{"id":471510,"date":"2018-03-05T13:49:33","date_gmt":"2018-03-05T21:49:33","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-research-item&p=471510"},"modified":"2019-02-19T12:06:58","modified_gmt":"2019-02-19T20:06:58","slug":"orthogonal-machine-learning-power-and-limitations","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/orthogonal-machine-learning-power-and-limitations\/","title":{"rendered":"Orthogonal Machine Learning: Power and Limitations"},"content":{"rendered":"
Double machine learning provides\u00a0\u221an-consistent estimates of parameters of interest even when high-dimensional or nonparametric nuisance parameters are estimated at an n<\/span>\u00a0\u2212<\/span>1<\/span>\/<\/span><\/span><\/span>4<\/span><\/span><\/span>\u00a0<\/span><\/span>\u00a0<\/span><\/span> rate. The key is to employ Neyman-orthogonal moment equations which are first-order insensitive to perturbations in the nuisance parameters. We show that the n<\/span>\u00a0\u2212<\/span>1<\/span>\/<\/span><\/span><\/span>4<\/span><\/span><\/span>\u00a0<\/span><\/span>\u00a0<\/span><\/span> requirement can be improved to n<\/span>\u00a0\u2212<\/span>1<\/span>\/<\/span><\/span><\/span>(<\/span>2<\/span>k<\/span>+<\/span>2<\/span>)<\/span><\/span><\/span>\u00a0<\/span><\/span>\u00a0<\/span><\/span> by employing a k<\/span><\/span>\u00a0<\/span><\/span> -th order notion of orthogonality that grants robustness to more complex or higher-dimensional nuisance parameters. In the partially linear regression setting popular in causal inference, we show that we can construct second-order orthogonal moments if and only if the treatment residual is not normally distributed. Our proof relies on Stein’s lemma and may be of independent interest. We conclude by demonstrating the robustness benefits of an explicit doubly-orthogonal estimation procedure for treatment effect.<\/p>\n","protected":false},"excerpt":{"rendered":" Double machine learning provides\u00a0\u221an-consistent estimates of parameters of interest even when high-dimensional or nonparametric nuisance parameters are estimated at an n\u00a0\u22121\/4\u00a0\u00a0 rate. The key is to employ Neyman-orthogonal moment equations which are first-order insensitive to perturbations in the nuisance parameters. We show that the n\u00a0\u22121\/4\u00a0\u00a0 requirement can be improved to n\u00a0\u22121\/(2k+2)\u00a0\u00a0 by employing a k\u00a0 […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13548],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-471510","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-economics","msr-locale-en_us"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2017-12-21","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"","msr_publicationurl":"https:\/\/arxiv.org\/pdf\/1711.00342.pdf","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/pdf\/1711.00342.pdf","label_id":"243109","label":0}],"msr_related_uploader":"","msr_attachments":[{"id":0,"url":"https:\/\/arxiv.org\/pdf\/1711.00342.pdf"}],"msr-author-ordering":[{"type":"user_nicename","value":"Lester Mackey","user_id":36161,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lester Mackey"},{"type":"user_nicename","value":"Vasilis Syrgkanis","user_id":34499,"rest_url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Vasilis Syrgkanis"},{"type":"text","value":"Ilias Zadik","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199563],"msr_event":[],"msr_group":[437316,656316],"msr_project":[656325,332666],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":656325,"post_title":"EconML","post_name":"econml","post_type":"msr-project","post_date":"2020-06-02 09:40:48","post_modified":"2022-02-24 07:11:27","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/econml\/","post_excerpt":"EconML\u00a0is an open source Python package developed by the ALICE team at Microsoft Research that applies the power of machine learning techniques to estimate individualized causal responses from observational or experimental data. The suite of estimation methods provided in EconML represents the latest advances in causal machine learning. By incorporating individual machine learning steps into interpretable causal models, these methods improve the reliability of what-if predictions and make causal analysis quicker and easier for a…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/656325"}]}},{"ID":332666,"post_title":"ALICE","post_name":"alice","post_type":"msr-project","post_date":"2016-12-08 05:45:31","post_modified":"2020-04-14 07:52:37","post_status":"publish","permalink":"https:\/\/www.microsoft.com\/en-us\/research\/project\/alice\/","post_excerpt":"ALICE Automated Learning and Intelligence for Causation and Economics Alice is a project to direct Artificial Intelligence towards economic decision making. We are building tools that combine state-of-the-art machine learning with econometrics \u2013 the measurement of economic systems -- in order to bring automation to economic decision making. The heart of this project is a striving to measure causation: if you want to understand or make policy decisions in a complex economy, you need to…","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/332666"}]}}]},"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/471510"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/471510\/revisions"}],"predecessor-version":[{"id":471522,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/471510\/revisions\/471522"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=471510"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=471510"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=471510"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=471510"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=471510"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=471510"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=471510"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=471510"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=471510"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=471510"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=471510"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=471510"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=471510"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=471510"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=471510"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=471510"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}