{ "id": "2006.10940", "version": "v1", "published": "2020-06-19T03:00:01.000Z", "updated": "2020-06-19T03:00:01.000Z", "title": "Open Problem: Model Selection for Contextual Bandits", "authors": [ "Dylan J. Foster", "Akshay Krishnamurthy", "Haipeng Luo" ], "comment": "COLT 2020 open problem", "categories": [ "cs.LG", "stat.ML" ], "abstract": "In statistical learning, algorithms for model selection allow the learner to adapt to the complexity of the best hypothesis class in a sequence. We ask whether similar guarantees are possible for contextual bandit learning.", "revisions": [ { "version": "v1", "updated": "2020-06-19T03:00:01.000Z" } ], "analyses": { "keywords": [ "model selection", "open problem", "best hypothesis class", "similar guarantees", "complexity" ], "note": { "typesetting": "TeX", "pages": 0, "language": "en", "license": "arXiv", "status": "editable" } } }