5 papers · 1 filter
Efficient and Noise-Tolerant PAC Learning of Multiclass Linear Classifiers
Rita Adhikari, Shiwei Zeng
Noise-tolerant PAC learning of linear models has been of central interests in machine learning community since the last century. In recent years, many computationally-efficient alg…
Attribute-Efficient PAC Learning of Sparse Halfspaces with Constant Malicious Noise Rate
Shiwei Zeng, Jie Shen
Attribute-efficient PAC learning of sparse halfspaces has been a fundamental problem in machine learning theory. In recent years, machine learning algorithms are faced with prevale…
List-Decodable Sparse Mean Estimation
Shiwei Zeng, Jie Shen
Robust mean estimation is one of the most important problems in statistics: given a set of samples in where an fraction are drawn from some distribution and…
Semi-verified PAC Learning from the Crowd
Shiwei Zeng, Jie Shen
We study the problem of crowdsourced PAC learning of threshold functions. This is a challenging problem and only recently have query-efficient algorithms been established under the…
Efficient PAC Learning from the Crowd with Pairwise Comparisons
Shiwei Zeng, Jie Shen
We study crowdsourced PAC learning of threshold functions, where the labels are gathered from a pool of annotators some of whom may behave adversarially. This is yet a challenging…