Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.13079 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913237974384640 |
|---|---|
| author | Arnal, Charles Cabannes, Vivien Perchet, Vianney |
| author_facet | Arnal, Charles Cabannes, Vivien Perchet, Vianney |
| contents | The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical frameworks. In this paper, we formalize core aspects of weakly supervised and active learning with a simple problem: the estimation of the mode of a distribution using partial feedback. We show how entropy coding allows for optimal information acquisition from partial feedback, develop coarse sufficient statistics for mode identification, and adapt bandit algorithms to our new setting. Finally, we combine those contributions into a statistically and computationally efficient solution to our problem. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_13079 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mode Estimation with Partial Feedback Arnal, Charles Cabannes, Vivien Perchet, Vianney Machine Learning Information Retrieval Information Theory 62L05, 62B86, 62D10, 62B10 The combination of lightly supervised pre-training and online fine-tuning has played a key role in recent AI developments. These new learning pipelines call for new theoretical frameworks. In this paper, we formalize core aspects of weakly supervised and active learning with a simple problem: the estimation of the mode of a distribution using partial feedback. We show how entropy coding allows for optimal information acquisition from partial feedback, develop coarse sufficient statistics for mode identification, and adapt bandit algorithms to our new setting. Finally, we combine those contributions into a statistically and computationally efficient solution to our problem. |
| title | Mode Estimation with Partial Feedback |
| topic | Machine Learning Information Retrieval Information Theory 62L05, 62B86, 62D10, 62B10 |
| url | https://arxiv.org/abs/2402.13079 |