Causal relationships are stable across distribution shifts. Models based on causal knowledge have the potential to generalize to unseen domains and offer counterfactual predictions: how do outcomes change if a certain feature is changed in the real world. In recent years, machine learning methods based on causal reasoning have led to advances in out-of-domain generalization, fairness and explanation, and robustness to data selection biases. \u00ac In this session, we discuss big ideas at the intersections of causal inference and machine learning towards building stable predictive models and discovering causal insights from data.<\/p>\n
Special MSR India session<\/p>\n
Session Lead: Amit Sharma, Microsoft<\/p>\n
Speaker: Susan Athey, Stanford University
\nTalk Title: Causal Inference, Consumer Choice, and the Value of Data<\/p>\n
Speaker: Elias Bareinboim, Columbia University
\nTalk Title: On the Causal Foundations of Artificial Intelligence (Explainability & Decision-Making)<\/p>\n
Speaker: Cheng Zhang, Microsoft
\nTalk Title: A causal view on Robustness of Neural Networks<\/p>\n
Q&A panel with all 3 speakers<\/p>\n","protected":false},"excerpt":{"rendered":"
Causal relationships are stable across distribution shifts. Models based on causal knowledge have the potential to generalize to unseen domains and offer counterfactual predictions: how do outcomes change if a certain feature is changed in the real world. In recent years, machine learning methods based on causal reasoning have led to advances in out-of-domain generalization, […]<\/p>\n","protected":false},"featured_media":679983,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13556],"msr-video-type":[],"msr-locale":[268875],"msr-post-option":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-679980","msr-video","type-msr-video","status-publish","has-post-thumbnail","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us"],"msr_download_urls":"","msr_external_url":"https:\/\/youtu.be\/wYVptiGkmQM","msr_secondary_video_url":"","msr_video_file":"","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/679980"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-video"}],"version-history":[{"count":1,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/679980\/revisions"}],"predecessor-version":[{"id":679986,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video\/679980\/revisions\/679986"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media\/679983"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=679980"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=679980"},{"taxonomy":"msr-video-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-video-type?post=679980"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=679980"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=679980"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=679980"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=679980"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}