Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms — DORM, DORM+, and AdaHedgeD — arise from a novel reduction of delayed online learning to optimistic online learning that reveals how optimistic hints can mitigate the regret penalty caused by delay. We pair this delay-as-optimism perspective with a new analysis of optimistic learning that exposes its robustness to hinting errors and a new meta-algorithm for learning effective hinting strategies in the presence of delay. We conclude by benchmarking our algorithms on four subseasonal climate forecasting tasks, demonstrating low regret relative to state-of-the-art forecasting models.<\/p>\n","protected":false},"excerpt":{"rendered":"
Inspired by the demands of real-time climate and weather forecasting, we develop optimistic online learning algorithms that require no parameter tuning and have optimal regret guarantees under delayed feedback. Our algorithms — DORM, DORM+, and AdaHedgeD — arise from a novel reduction of delayed online learning to optimistic online learning that reveals how optimistic hints […]<\/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":"","msr-author-ordering":[{"type":"text","value":"Genevieve Flaspohler","user_id":0},{"type":"text","value":"Francesco Orabona","user_id":0},{"type":"text","value":"Judah Cohen","user_id":0},{"type":"text","value":"Soukayna Mouatadid","user_id":0},{"type":"user_nicename","value":"Miruna Oprescu","user_id":"37353"},{"type":"text","value":"Paulo Orenstein","user_id":0},{"type":"user_nicename","value":"Lester Mackey","user_id":"36161"}],"msr_publishername":"","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"","msr_page_range_end":"","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"2021 International Conference on Machine Learning","msr_doi":"","msr_arxiv_id":"","msr_mag_id":"3171900464","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_release_tracker_id":"","msr_highlight_type":"","msr_date_display_format":"","msr_main_download_label":"","msr_external_link_label":"","msr_doi_label":"","msr_published_date":"2021-07-17","msr_startdate":"","msr_presentation_date":"","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"https:\/\/icml.cc\/","msr_journal_url":"","msr_year":2021,"msr_month":7,"msr_day":17,"msr_microsoftintellectualproperty":true,"msr_pub_id":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":false,"title":"https:\/\/arxiv.org\/abs\/2106.06885","label_id":243109,"label":0}],"msr_related_uploader":[],"msr_original_fields_of_study":["Machine learning","Computer science","Artificial intelligence","Robustness (computer science)","Regret","Online learning","Benchmarking","Reduction (complexity)","Weather forecasting","Optimism"],"msr_s2_paper_id":"","msr_s2_pdf_url":"","msr_citation_count_updated":"","msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13556],"msr-publication-type":[193716],"msr-publisher":[],"msr-publication-cta":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246694,251857,246691,246685,246844,257986,255385,246823,246754,257983],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-760393","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-field-of-study-artificial-intelligence","msr-field-of-study-benchmarking","msr-field-of-study-computer-science","msr-field-of-study-machine-learning","msr-field-of-study-online-learning","msr-field-of-study-optimism","msr-field-of-study-reduction-complexity","msr-field-of-study-regret","msr-field-of-study-robustness-computer-science","msr-field-of-study-weather-forecasting"],"msr_publishername":"","msr_edition":"","msr_affiliation":"","msr_published_date":"2021-07-17","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":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/arxiv.org\/abs\/2106.06885","label_id":"243109","label":0}],"msr_related_uploader":[],"msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"text","value":"Genevieve Flaspohler","user_id":0,"rest_url":false},{"type":"text","value":"Francesco Orabona","user_id":0,"rest_url":false},{"type":"text","value":"Judah Cohen","user_id":0,"rest_url":false},{"type":"text","value":"Soukayna Mouatadid","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Miruna Oprescu","user_id":37353,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Miruna Oprescu"},{"type":"text","value":"Paulo Orenstein","user_id":0,"rest_url":false},{"type":"user_nicename","value":"Lester Mackey","user_id":36161,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Lester Mackey"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[740803],"msr_group":[847351],"msr_project":[608757],"publication":[],"video":[],"msr-tool":[778384],"msr_publication_type":"inproceedings","related_content":{"projects":[{"ID":608757,"post_title":"Subseasonal Climate Forecasting","post_name":"subseasonal-climate-forecasting","post_type":"msr-project","post_date":"2019-09-16 06:15:14","post_modified":"2026-09-04 11:47:58","post_status":"publish","permalink":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/project\/subseasonal-climate-forecasting\/","post_excerpt":"Decision-makers rely on weather forecasts to plant crops, manage wildfires, allocate water and energy, and prepare for weather extremes. Today, such forecasts enjoy unprecedented accuracy out to two weeks thanks to steady advances in physics-based dynamical models and data-driven artificial intelligence (AI) models. However, model skill drops precipitously at subseasonal timescales (2 - 6 weeks ahead), due to compounding errors, systemic model biases, and the chaotic nature of the atmosphere.","_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/608757"}]}}]},"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/760393","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/760393\/revisions"}],"predecessor-version":[{"id":760396,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/760393\/revisions\/760396"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=760393"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=760393"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=760393"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=760393"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=760393"},{"taxonomy":"msr-publication-cta","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-cta?post=760393"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=760393"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=760393"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=760393"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=760393"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=760393"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=760393"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=760393"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=760393"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}