On biased random walks, corrupted intervals, and learning under adversarial design
On biased random walks, corrupted intervals, and learning under adversarial design
复制标题
DOI:
10.1007/s10472-020-09696-1
复制
发表时间:
2020-03
影响因子:
1.2
通讯作者:
D. Berend;A. Kontorovich;L. Reyzin;Thomas Robinson
中科院分区:
文献类型:
--
作者:
D. Berend;A. Kontorovich;L. Reyzin;Thomas Robinson
We tackle some fundamental problems in probability theory on corrupted random processes on the integer line. We analyze when a biased random walk is expected to reach its bottommost point and when intervals of integer points can be detected under a natural model of noise. We apply these results to problems in learning thresholds and intervals under a new model for learning under adversarial design.