Corpus ID: 220127906

Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries

@article{Kumar2020AveragecaseCO,
  title={Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries},
  author={Akash Kumar and A. Singla and Yisong Yue and Yuxin Chen},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.14677}
}
We examine the task of locating a target region among those induced by intersections of n halfspaces in R^d. This generic task connects to fundamental machine learning problems, such as training a perceptron and learning a ϕ-separable dichotomy. We investigate the average teaching complexity of the task, i.e., the minimal number of samples (halfspace queries) required by a teacher to help a version-space learner in locating a randomly selected target. As our main result, we show that the… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 55 REFERENCES
PAC learning intersections of halfspaces with membership queries (extended abstract)
Recursive teaching dimension, VC-dimension and sample compression
DNF Are Teachable in the Average Case
Open Problem: Recursive Teaching Dimension Versus VC Dimension
On the hardness of learning intersections of two halfspaces
Active Classification with Comparison Queries
Minimax Analysis of Active Learning
Learning an Intersection of a Constant Number of Halfspaces over a Uniform Distribution
Learning intersections and thresholds of halfspaces
...
1
2
3
4
5
...