Learning from untrusted data

DOI10.1145/3055399.3055491zbMath1369.68277arXiv1611.02315OpenAlexW2554864439MaRDI QIDQ4977960

Gregory Valiant, Jacob Steinhardt, Moses Charikar

Publication date: 17 August 2017

Published in: Proceedings of the 49th Annual ACM SIGACT Symposium on Theory of Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1611.02315

zbMATH Keywords

high-dimensional statisticsrobust learningoutlier removal

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (17)

Sampling Correctors ⋮ Stronger data poisoning attacks break data sanitization defenses ⋮ Best Arm Identification for Contaminated Bandits ⋮ Efficient parameter estimation of truncated Boolean product distributions ⋮ Unnamed Item ⋮ Robust supervised learning with coordinate gradient descent ⋮ Learning under \(p\)-tampering poisoning attacks ⋮ Unnamed Item ⋮ Resilience: A Criterion for Learning in the Presence of Arbitrary Outliers ⋮ Robust Estimators in High-Dimensions Without the Computational Intractability ⋮ Corruption-tolerant bandit learning ⋮ A characterization of list learnability ⋮ Algorithms approaching the threshold for semi-random planted clique ⋮ Distributed statistical estimation and rates of convergence in normal approximation ⋮ Mean estimation and regression under heavy-tailed distributions: A survey ⋮ Nearly optimal robust secret sharing against rushing adversaries ⋮ Unnamed Item

This page was built for publication: Learning from untrusted data