A Note on Learning from Multiple-Instance Examples
暂无分享,去创建一个
We describe a simple reduction from the problem of PAC-learning from multiple-instance examples to that of PAC-learning with one-sided random classification noise. Thus, all concept classes learnable with one-sided noise, which includes all concepts learnable in the usual 2-sided random noise model plus others such as the parity function, are learnable from multiple-instance examples. We also describe a more efficient (and somewhat technically more involved) reduction to the Statistical-Query model that results in a polynomial-time algorithm for learning axis-parallel rectangles with sample complexity Õ(d2r/ε2) , saving roughly a factor of r over the results of Auer et al. (1997).
[1] Thomas G. Dietterich,et al. Solving the Multiple Instance Problem with Axis-Parallel Rectangles , 1997, Artif. Intell..
[2] Philip M. Long,et al. PAC Learning Axis-aligned Rectangles with Respect to Product Distributions from Multiple-Instance Examples , 1996, COLT '96.
[3] Peter Auer,et al. On Learning From Multi-Instance Examples: Empirical Evaluation of a Theoretical Approach , 1997, ICML.
[4] Aravind Srinivasan,et al. Approximating hyper-rectangles: learning and pseudo-random sets , 1997, STOC '97.