Learning unions of high-dimensional boxes over the reals

Abstract Beimel and Kushilevitz (1997) presented an algorithm that exactly learns (using membership queries and equivalence queries) several classes of unions of boxes in high dimension over finite discrete domains. The running time of the algorithm is polynomial in the logarithm of the size of the domain and other parameters of the target function (in particular, the dimension). We go one step further and present a PAC+MQ algorithm whose running time is independent of the size of the domain. Thus, we can learn such classes of boxes over infinite domains. Specifically, we learn unions of t disjoint n -dimensional boxes over the reals in time polynomial in n and t , and unions of O(log n ) (possibly intersecting) n -dimensional boxes over the reals in time polynomial in n .

[1]  Philip M. Long,et al.  Composite geometric concepts and polynomial predictability , 1990, COLT '90.

[2]  Eyal Kushilevitz,et al.  Learning Boxes in High Dimension , 1998, Algorithmica.

[3]  Zhixiang Chen,et al.  On learning discretized geometric concepts , 1994, Proceedings 35th Annual Symposium on Foundations of Computer Science.

[4]  Michael Clausen,et al.  Algebraic complexity theory , 1997, Grundlehren der mathematischen Wissenschaften.

[5]  W. Maass,et al.  Eecient Learning with Virtual Threshold Gates , 1997 .

[6]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, CACM.

[7]  Stephen Kwek,et al.  PAC Learning Intersections of Halfspaces with Membership Queries , 1998, Algorithmica.

[8]  Michael Frazier,et al.  Learning from a consistently ignorant teacher , 1994, COLT '94.

[9]  Michael Kearns,et al.  Efficient noise-tolerant learning from statistical queries , 1993, STOC.

[10]  Lenore Blum,et al.  Complexity and Real Computation , 1997, Springer New York.

[11]  Shai Ben-David,et al.  A composition theorem for learning algorithms with applications to geometric concept classes , 1997, STOC '97.

[12]  David Haussler,et al.  Learnability and the Vapnik-Chervonenkis dimension , 1989, JACM.

[13]  Aravind Srinivasan,et al.  Approximating hyper-rectangles: learning and pseudo-random sets , 1997, STOC '97.

[14]  Umesh V. Vazirani,et al.  An Introduction to Computational Learning Theory , 1994 .

[15]  Eyal Kushilevitz,et al.  On the applications of multiplicity automata in learning , 1996, Proceedings of 37th Conference on Foundations of Computer Science.

[16]  Patrick Brézillon,et al.  Lecture Notes in Artificial Intelligence , 1999 .

[17]  Aravind Srinivasan,et al.  Approximating Hyper-Rectangles: Learning and Pseudorandom Sets , 1998, J. Comput. Syst. Sci..

[18]  Manfred K. Warmuth,et al.  Efficient Learning With Virtual Threshold Gates , 1995, Inf. Comput..