A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugates
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911265901772800 |
|---|---|
| author | Lee, Wei-Cheng Orabona, Francesco |
| author_facet | Lee, Wei-Cheng Orabona, Francesco |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11211 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugates Lee, Wei-Cheng Orabona, Francesco Machine Learning Optimization and Control 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. |
| title | A Best-of-Both-Worlds Proof for Tsallis-INF without Fenchel Conjugates |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2511.11211 |