Learning in the Presence of Malicious Errors

DOI10.1137/0222052zbMATH Open0789.68118OpenAlexW1968998685MaRDI QIDQ3137710FDOQ3137710

Authors: Michael Kearns, Ming Li 

Publication date: 10 October 1993

Published in: SIAM Journal on Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1137/0222052

Recommendations

• Sample-efficient strategies for learning in the presence of noise
• scientific article; zbMATH DE number 1256729
• Learning with errors in answers to membership queries
• Malicious omissions and errors in answers to membership queries
• On-line learning with malicious noise and the closure algorithm

zbMATH Keywords

optimal learning algorithmsdistribution-free model of learningtolerance to errors

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cited In (50)

• Augmented Learning with Errors: The Untapped Potential of the Error Term
• Learning fallible deterministic finite automata
• Boosting in the presence of outliers: adaptive classification with nonconvex loss functions
• Realizable learning is all you need
• Learning to Recognize Three-Dimensional Objects
• Learning Halfspaces with Malicious Noise
• Robust estimators in high-dimensions without the computational intractability
• Classic learning
• An improved branch-and-bound method for maximum monomial agreement
• Can PAC learning algorithms tolerate random attribute noise?
• Stronger data poisoning attacks break data sanitization defenses
• An experimental evaluation of simplicity in rule learning
• Watermarking cryptographic capabilities
• Learning conjunctions with noise under product distributions
• Knowing what doesn't matter: exploiting the omission of irrelevant data
• Learning with restricted focus of attention
• Reliable agnostic learning
• Adversarial machine learning for cybersecurity and computer vision: current developments and challenges
• PAC learning with nasty noise.
• Statistical computational learning
• Learning nested differences in the presence of malicious noise
• Learning nested differences in the presence of malicious noise
• Incentive compatible regression learning
• Exact learning from an honest teacher that answers membership queries
• Data poisoning against information-theoretic feature selection
• Apple tasting.
• Detecting and preventing error propagation via competitive learning
• On the robustness of randomized classifiers to adversarial examples
• Robust logics
• Maximizing agreements with one-sided error with applications to heuristic learning
• Learning with unreliable boundary queries
• Specification and simulation of statistical query algorithms for efficiency and noise tolerance
• Toward efficient agnostic learning
• DNA sequencing and string learning
• Maximizing agreements with one-sided error with applications to heuristic learning
• Best arm identification for contaminated bandits
• Learning Kernel Perceptrons on Noisy Data Using Random Projections
• Recursive reasoning-based training-time adversarial machine learning
• On domain-partitioning induction criteria: worst-case bounds for the worst-case based
• Robust multivariate mean estimation: the optimality of trimmed mean
• New Algorithms for Learning in Presence of Errors
• The security of machine learning
• Robust and efficient mean estimation: an approach based on the properties of self-normalized sums
• Improved lower bounds for learning from noisy examples: An information-theoretic approach
• Machine learning in adversarial environments
• On the difficulty of approximately maximizing agreements.
• Learning under \(p\)-tampering poisoning attacks
• Maximizing agreements and coagnostic learning
• Exact Learning of Discretized Geometric Concepts
• Four types of noise in data for PAC learning

This page was built for publication: Learning in the Presence of Malicious Errors

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3137710)