paper-with-me

Papers

Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov noise

2021-02-10 · Chicheng Zhang, Yinan Li

We give a computationally-efficient PAC active learning algorithm for $d$-dimensional homogeneous halfspaces that can tolerate Massart noise (Massart and N\'ed\'elec, 2006) and Tsybakov noise (Tsybakov, 2004). Specialized to the $\eta$-Massart noise setting, our algorithm achieves an information-theoretically near-optimal label complexity of $\tilde{O}\left( \frac{d}{(1-2\eta)^2} \mathrm{polylog}(\frac1\epsilon) \right)$ under a wide range of unlabeled data distributions (specifically, the family of "structured distributions" defined in Diakonikolas et al. (2020)). Under the more challenging Tsybakov noise condition, we identify two subfamilies of noise conditions, under which our efficient algorithm provides label complexity guarantees strictly lower than passive learning algorithms.

📄 PDF Abstract BibTeX arXiv:2102.05312

Code (0)

등록된 구현이 없습니다.

Tasks

Active Learning

Similar Papers 제목 키워드 기반

Efficient Active Learning Halfspaces with Tsybakov Noise: A Non-convex Optimization Approach

2023-10-23 · Yinan Li, Chicheng Zhang

We study the problem of computationally and label efficient PAC active learning $d$-dimensional halfspaces with Tsybakov Noise~\citep{tsybakov2004optimal} under structured unlabeled data distributions. Inspired by~\cite{…

Active Learning

Learning Halfspaces with Tsybakov Noise

2020-06-11 · Ilias Diakonikolas, Vasilis Kontonis, Christos Tzamos, Nikos Zarifis

We study the efficient PAC learnability of halfspaces in the presence of Tsybakov noise. In the Tsybakov noise model, each label is independently flipped with some probability which is controlled by an adversary. This no…

PAC learning

Optimal SQ Lower Bounds for Learning Halfspaces with Massart Noise

2022-01-24 · Rajai Nasser, Stefan Tiegel

We give tight statistical query (SQ) lower bounds for learnining halfspaces in the presence of Massart noise. In particular, suppose that all labels are corrupted with probability at most $\eta$. We show that for arbitra…

Near-Optimal Statistical Query Hardness of Learning Halfspaces with Massart Noise

2020-12-17 · Ilias Diakonikolas, Daniel M. Kane

We study the problem of PAC learning halfspaces with Massart noise. Given labeled samples $(x, y)$ from a distribution $D$ on $\mathbb{R}^{d} \times \{ \pm 1\}$ such that the marginal $D_x$ on the examples is arbitrary a…

Learning TheoryPAC learning

Classification Under Misspecification: Halfspaces, Generalized Linear Models, and Connections to Evolvability

2020-06-08 · Sitan Chen, Frederic Koehler, Ankur Moitra, Morris Yau

In this paper we revisit some classic problems on classification under misspecification. In particular, we study the problem of learning halfspaces under Massart noise with rate $\eta$. In a recent work, Diakonikolas, Go…

FairnessGeneral ClassificationKnowledge Distillation