On Biased Random Walks, Corrupted Intervals, and Learning Under Adversarial Design
Machine Learning
2020-03-31 v1 Probability
Machine Learning
Abstract
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.
Cite
@article{arxiv.2003.13561,
title = {On Biased Random Walks, Corrupted Intervals, and Learning Under Adversarial Design},
author = {Daniel Berend and Aryeh Kontorovich and Lev Reyzin and Thomas Robinson},
journal= {arXiv preprint arXiv:2003.13561},
year = {2020}
}
Comments
18 pages