{"publist_id":"4819","date_updated":"2021-01-12T06:55:43Z","volume":51,"extern":"1","type":"journal_article","intvolume":"        51","language":[{"iso":"eng"}],"_id":"2165","main_file_link":[{"open_access":"1","url":"http://arxiv.org/abs/1410.0334"}],"doi":"10.1016/j.patrec.2014.08.013","author":[{"last_name":"Morvant","id":"4BAC2A72-F248-11E8-B48F-1D18A9856A87","full_name":"Morvant, Emilie","first_name":"Emilie","orcid":"0000-0002-8301-7240"}],"quality_controlled":"1","title":"Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling","publication":"Pattern Recognition Letters","publication_status":"published","oa_version":"Submitted Version","abstract":[{"lang":"eng","text":"In machine learning, the domain adaptation problem arrives when the test (tar-get) and the train (source) data are generated from different distributions.  A key applied issue is thus the design of algorithms able to generalize on a new distribution,  for which we have no label information.  We focus on learning classification models defined as a weighted majority vote over a set of real-valued functions. In this context, Germain et al. (2013) have shown that a measure of disagreement between these functions is crucial to control. The core of this measure is a theoretical bound—the C-bound (Lacasse et al., 2007)—which involves the disagreement and leads to a well performing majority vote learn-ing algorithm in usual non-adaptative supervised setting: MinCq. In this work,we propose a framework to extend MinCq to a domain adaptation scenario.This procedure takes advantage of the recent perturbed variation divergence between distributions proposed by Harel and Mannor (2012).  Justified by a theoretical bound on the target risk of the vote,  we provide to MinCq a tar-get sample labeled thanks to a perturbed variation-based self-labeling focused on the regions where the source and target marginals appear similar.  We also study the influence of our self-labeling, from which we deduce an original process for tuning the hyperparameters. Finally, our framework called PV-MinCq shows very promising results on a rotation and translation synthetic problem."}],"citation":{"ieee":"E. Morvant, “Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling,” <i>Pattern Recognition Letters</i>, vol. 51. Elsevier, pp. 37–43, 2014.","short":"E. Morvant, Pattern Recognition Letters 51 (2014) 37–43.","mla":"Morvant, Emilie. “Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling.” <i>Pattern Recognition Letters</i>, vol. 51, Elsevier, 2014, pp. 37–43, doi:<a href=\"https://doi.org/10.1016/j.patrec.2014.08.013\">10.1016/j.patrec.2014.08.013</a>.","ama":"Morvant E. Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling. <i>Pattern Recognition Letters</i>. 2014;51:37-43. doi:<a href=\"https://doi.org/10.1016/j.patrec.2014.08.013\">10.1016/j.patrec.2014.08.013</a>","apa":"Morvant, E. (2014). Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling. <i>Pattern Recognition Letters</i>. Elsevier. <a href=\"https://doi.org/10.1016/j.patrec.2014.08.013\">https://doi.org/10.1016/j.patrec.2014.08.013</a>","ista":"Morvant E. 2014. Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling. Pattern Recognition Letters. 51, 37–43.","chicago":"Morvant, Emilie. “Domain Adaptation of Weighted Majority Votes via Perturbed Variation-Based Self-Labeling.” <i>Pattern Recognition Letters</i>. Elsevier, 2014. <a href=\"https://doi.org/10.1016/j.patrec.2014.08.013\">https://doi.org/10.1016/j.patrec.2014.08.013</a>."},"month":"10","date_created":"2018-12-11T11:56:05Z","project":[{"call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding","grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425"}],"status":"public","year":"2014","publisher":"Elsevier","page":"37-43","ec_funded":1,"day":"01","user_id":"4435EBFC-F248-11E8-B48F-1D18A9856A87","date_published":"2014-10-01T00:00:00Z","oa":1}