On biased random walks, corrupted intervals, and learning under adversarial design

DOI10.1007/s10472-020-09696-1zbMath1460.60034arXiv2003.13561OpenAlexW3027765863MaRDI QIDQ2202524

Lev Reyzin, Daniel Berend, Thomas J. Robinson, Leonid (Aryeh) Kontorovich

Publication date: 18 September 2020

Published in: Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2003.13561

zbMATH Keywords

random walksclassification noiseadversarial learning

Mathematics Subject Classification ID

Sums of independent random variables; random walks (60G50) Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• Generalization bounds of ERM algorithm with Markov chain samples
• Buy low, sell high
• Risk bounds for statistical learning
• Learning from dependent observations
• Efficient distribution-free learning of probabilistic concepts
• Toward efficient agnostic learning
• Rates of uniform convergence of empirical means with mixing processes
• No more than three favorite sites for simple random walk
• The Generalization Ability of Online Algorithms for Dependent Data
• 10.1162/153244303765208368
• Efficient noise-tolerant learning from statistical queries
• Smallest singular value of a random rectangular matrix
• A theory of the learnable
• Extension of the PAC framework to finite and countable Markov chains
• Structural risk minimization over data-dependent hierarchies
• Prediction, Learning, and Games
• The Number of Linearly Inducible Orderings of Points in d-Space
• Introduction to nonparametric estimation
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: On biased random walks, corrupted intervals, and learning under adversarial design