{"ID":2841669,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11211","arxiv_id":"2511.11211","title":"A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugates","abstract":"In this short note, we present a simple derivation of the best-of-both-world guarantee for the Tsallis-INF multi-armed bandit algorithm from J. Zimmert and Y. Seldin. Tsallis-INF: An optimal algorithm for stochastic and adversarial bandits. Journal of Machine Learning Research, 22(28):1-49, 2021. URL https://jmlr.csail.mit.edu/papers/volume22/19-753/19-753.pdf. In particular, the proof uses modern tools from online convex optimization and avoid the use of conjugate functions. Also, we do not optimize the constants in the bounds in favor of a slimmer proof.","short_abstract":"In this short note, we present a simple derivation of the best-of-both-world guarantee for the Tsallis-INF multi-armed bandit algorithm from J. Zimmert and Y. Seldin. Tsallis-INF: An optimal algorithm for stochastic and adversarial bandits. Journal of Machine Learning Research, 22(28):1-49, 2021. URL https://jmlr.csail...","url_abs":"https://arxiv.org/abs/2511.11211","url_pdf":"https://arxiv.org/pdf/2511.11211v1","authors":"[\"Wei-Cheng Lee\",\"Francesco Orabona\"]","published":"2025-11-14T12:10:23Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"math.OC\",\"stat.ML\"]","methods":"[]","project_urls":"[\"https://jmlr.csail.mit.edu/papers/volume22/19-753/19-753.pdf\"]","has_code":false}