Online Algorithm for Aggregating Experts' Predictions with Unbounded Quadratic Loss
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910780724609024 |
|---|---|
| author | Korotin, Alexander V'yugin, Vladimir Burnaev, Evgeny |
| author_facet | Korotin, Alexander V'yugin, Vladimir Burnaev, Evgeny |
| contents | We consider the problem of online aggregation of expert predictions with the quadratic loss function. We propose an algorithm for aggregating expert predictions which does not require a prior knowledge of the upper bound on the losses. The algorithm is based on the exponential reweighing of expert losses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_06505 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Online Algorithm for Aggregating Experts' Predictions with Unbounded Quadratic Loss Korotin, Alexander V'yugin, Vladimir Burnaev, Evgeny Machine Learning We consider the problem of online aggregation of expert predictions with the quadratic loss function. We propose an algorithm for aggregating expert predictions which does not require a prior knowledge of the upper bound on the losses. The algorithm is based on the exponential reweighing of expert losses. |
| title | Online Algorithm for Aggregating Experts' Predictions with Unbounded Quadratic Loss |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.06505 |