Online Learning of Halfspaces with Massart Noise
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916254723342336 |
|---|---|
| author | Diakonikolas, Ilias Kontonis, Vasilis Tzamos, Christos Zarifis, Nikos |
| author_facet | Diakonikolas, Ilias Kontonis, Vasilis Tzamos, Christos Zarifis, Nikos |
| contents | We study the task of online learning in the presence of Massart noise. Instead of assuming that the online adversary chooses an arbitrary sequence of labels, we assume that the context $\mathbf{x}$ is selected adversarially but the label $y$ presented to the learner disagrees with the ground-truth label of $\mathbf{x}$ with unknown probability at most $η$. We study the fundamental class of $γ$-margin linear classifiers and present a computationally efficient algorithm that achieves mistake bound $ηT + o(T)$. Our mistake bound is qualitatively tight for efficient algorithms: it is known that even in the offline setting achieving classification error better than $η$ requires super-polynomial time in the SQ model.
We extend our online learning model to a $k$-arm contextual bandit setting where the rewards -- instead of satisfying commonly used realizability assumptions -- are consistent (in expectation) with some linear ranking function with weight vector $\mathbf{w}^\ast$. Given a list of contexts $\mathbf{x}_1,\ldots \mathbf{x}_k$, if $\mathbf{w}^*\cdot \mathbf{x}_i > \mathbf{w}^* \cdot \mathbf{x}_j$, the expected reward of action $i$ must be larger than that of $j$ by at least $Δ$. We use our Massart online learner to design an efficient bandit algorithm that obtains expected reward at least $(1-1/k)~ ΔT - o(T)$ bigger than choosing a random action at every round. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_12958 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Online Learning of Halfspaces with Massart Noise Diakonikolas, Ilias Kontonis, Vasilis Tzamos, Christos Zarifis, Nikos Machine Learning Data Structures and Algorithms Statistics Theory We study the task of online learning in the presence of Massart noise. Instead of assuming that the online adversary chooses an arbitrary sequence of labels, we assume that the context $\mathbf{x}$ is selected adversarially but the label $y$ presented to the learner disagrees with the ground-truth label of $\mathbf{x}$ with unknown probability at most $η$. We study the fundamental class of $γ$-margin linear classifiers and present a computationally efficient algorithm that achieves mistake bound $ηT + o(T)$. Our mistake bound is qualitatively tight for efficient algorithms: it is known that even in the offline setting achieving classification error better than $η$ requires super-polynomial time in the SQ model. We extend our online learning model to a $k$-arm contextual bandit setting where the rewards -- instead of satisfying commonly used realizability assumptions -- are consistent (in expectation) with some linear ranking function with weight vector $\mathbf{w}^\ast$. Given a list of contexts $\mathbf{x}_1,\ldots \mathbf{x}_k$, if $\mathbf{w}^*\cdot \mathbf{x}_i > \mathbf{w}^* \cdot \mathbf{x}_j$, the expected reward of action $i$ must be larger than that of $j$ by at least $Δ$. We use our Massart online learner to design an efficient bandit algorithm that obtains expected reward at least $(1-1/k)~ ΔT - o(T)$ bigger than choosing a random action at every round. |
| title | Online Learning of Halfspaces with Massart Noise |
| topic | Machine Learning Data Structures and Algorithms Statistics Theory |
| url | https://arxiv.org/abs/2405.12958 |