{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,24]],"date-time":"2024-07-24T09:17:20Z","timestamp":1721812640223},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"04","license":[{"start":{"date-parts":[[2020,4,3]],"date-time":"2020-04-03T00:00:00Z","timestamp":1585872000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.aaai.org"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AAAI"],"abstract":"This manuscript introduces the idea of using Distributionally Robust Optimization (DRO) for the Counterfactual Risk Minimization (CRM) problem. Tapping into a rich existing literature, we show that DRO is a principled tool for counterfactual decision making. We also show that well-established solutions to the CRM problem like sample variance penalization schemes are special instances of a more general DRO problem. In this unifying framework, a variety of distributionally robust counterfactual risk estimators can be constructed using various probability distances and divergences as uncertainty measures. We propose the use of Kullback-Leibler divergence as an alternative way to model uncertainty in CRM and derive a new robust counterfactual objective. In our experiments, we show that this approach outperforms the state-of-the-art on four benchmark datasets, validating the relevance of using other uncertainty measures in practical applications.<\/jats:p>","DOI":"10.1609\/aaai.v34i04.5797","type":"journal-article","created":{"date-parts":[[2020,6,29]],"date-time":"2020-06-29T21:24:29Z","timestamp":1593465869000},"page":"3850-3857","source":"Crossref","is-referenced-by-count":11,"title":["Distributionally Robust Counterfactual Risk Minimization"],"prefix":"10.1609","volume":"34","author":[{"given":"Louis","family":"Faury","sequence":"first","affiliation":[]},{"given":"Ugo","family":"Tanielian","sequence":"additional","affiliation":[]},{"given":"Elvis","family":"Dohmatob","sequence":"additional","affiliation":[]},{"given":"Elena","family":"Smirnova","sequence":"additional","affiliation":[]},{"given":"Flavian","family":"Vasile","sequence":"additional","affiliation":[]}],"member":"9382","published-online":{"date-parts":[[2020,4,3]]},"container-title":["Proceedings of the AAAI Conference on Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/5797\/5653","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/download\/5797\/5653","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T23:57:43Z","timestamp":1667519863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/5797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,4,3]]},"references-count":0,"journal-issue":{"issue":"04","published-online":{"date-parts":[[2020,6,16]]}},"URL":"https:\/\/doi.org\/10.1609\/aaai.v34i04.5797","relation":{},"ISSN":["2374-3468","2159-5399"],"issn-type":[{"value":"2374-3468","type":"electronic"},{"value":"2159-5399","type":"print"}],"subject":[],"published":{"date-parts":[[2020,4,3]]}}}