{"publist_id":"5781","quality_controlled":"1","date_published":"2015-01-01T00:00:00Z","citation":{"apa":"Pentina, A., &#38; Lampert, C. (2015). Lifelong learning with non-i.i.d. tasks (Vol. 2015, pp. 1540–1548). Presented at the NIPS: Neural Information Processing Systems, Montreal, Canada: Neural Information Processing Systems.","chicago":"Pentina, Anastasia, and Christoph Lampert. “Lifelong Learning with Non-i.i.d. Tasks,” 2015:1540–48. Neural Information Processing Systems, 2015.","ieee":"A. Pentina and C. Lampert, “Lifelong learning with non-i.i.d. tasks,” presented at the NIPS: Neural Information Processing Systems, Montreal, Canada, 2015, vol. 2015, pp. 1540–1548.","ama":"Pentina A, Lampert C. Lifelong learning with non-i.i.d. tasks. In: Vol 2015. Neural Information Processing Systems; 2015:1540-1548.","mla":"Pentina, Anastasia, and Christoph Lampert. <i>Lifelong Learning with Non-i.i.d. Tasks</i>. Vol. 2015, Neural Information Processing Systems, 2015, pp. 1540–48.","ista":"Pentina A, Lampert C. 2015. Lifelong learning with non-i.i.d. tasks. NIPS: Neural Information Processing Systems, Advances in Neural Information Processing Systems, vol. 2015, 1540–1548.","short":"A. Pentina, C. Lampert, in:, Neural Information Processing Systems, 2015, pp. 1540–1548."},"ec_funded":1,"alternative_title":["Advances in Neural Information Processing Systems"],"intvolume":"      2015","oa":1,"title":"Lifelong learning with non-i.i.d. tasks","day":"01","main_file_link":[{"url":"http://papers.nips.cc/paper/6007-lifelong-learning-with-non-iid-tasks","open_access":"1"}],"publisher":"Neural Information Processing Systems","type":"conference","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","abstract":[{"lang":"eng","text":"In this work we aim at extending the theoretical foundations of lifelong learning. Previous work analyzing this scenario is based on the assumption that learning tasks are sampled i.i.d. from a task environment or limited to strongly constrained data distributions. Instead, we study two scenarios when lifelong learning is possible, even though the observed tasks do not form an i.i.d. sample: first, when they are sampled from the same environment, but possibly with dependencies, and second, when the task environment is allowed to change over time in a consistent way. In the first case we prove a PAC-Bayesian theorem that can be seen as a direct generalization of the analogous previous result for the i.i.d. case. For the second scenario we propose to learn an inductive bias in form of a transfer procedure. We present a generalization bound and show on a toy example how it can be used to identify a beneficial transfer algorithm."}],"scopus_import":1,"oa_version":"None","project":[{"grant_number":"308036","_id":"2532554C-B435-11E9-9278-68D0E5697425","call_identifier":"FP7","name":"Lifelong Learning of Visual Scene Understanding"}],"publication_status":"published","month":"01","conference":{"name":"NIPS: Neural Information Processing Systems","start_date":"2015-12-07","location":"Montreal, Canada","end_date":"2015-12-12"},"date_updated":"2021-01-12T06:50:39Z","date_created":"2018-12-11T11:51:57Z","volume":2015,"year":"2015","language":[{"iso":"eng"}],"page":"1540 - 1548","author":[{"first_name":"Anastasia","last_name":"Pentina","full_name":"Pentina, Anastasia","id":"42E87FC6-F248-11E8-B48F-1D18A9856A87"},{"first_name":"Christoph","last_name":"Lampert","full_name":"Lampert, Christoph","id":"40C20FD2-F248-11E8-B48F-1D18A9856A87","orcid":"0000-0001-8622-7887"}],"department":[{"_id":"ChLa"}],"status":"public","_id":"1425"}