Efficient noise-tolerant learning from statistical queries

DOI10.1145/167088.167200zbMath1310.68179OpenAlexW2072631813MaRDI QIDQ5248508

Michael Kearns

Publication date: 7 May 2015

Published in: Proceedings of the twenty-fifth annual ACM symposium on Theory of computing - STOC '93 (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/167088.167200

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Related Items

On universal learning algorithms, Learning unions of high-dimensional boxes over the reals, Classification with asymmetric label noise: consistency and maximal denoising, Simple learning algorithms using divide and conquer, Learning an intersection of a constant number of halfspaces over a uniform distribution, Learning fallible deterministic finite automata, Grey-box steganography, Learning nested differences in the presence of malicious noise, How to deal with malicious users in privacy‐preserving distributed data mining, A computational learning theory of active object recognition under uncertainty, \(P\)-sufficient statistics for PAC learning \(k\)-term-DNF formulas through enumeration, Four types of noise in data for PAC learning, On the noise estimation statistics, Grey-Box Steganography, Gaining degrees of freedom in subsymbolic learning, Agnostic learning of geometric patterns, New lower bounds for statistical query learning, Unnamed Item, An improved algorithm for learning sparse parities in the presence of noise, Four heads are better than three, Robust logics, Unconditional lower bounds for learning intersections of halfspaces, Generalized Learning Problems and Applications to Non-commutative Cryptography, General bounds on statistical query learning and PAC learning with noise via hypothesis boosting, On the learnability and usage of acyclic probabilistic finite automata, Specification and simulation of statistical query algorithms for efficiency and noise tolerance, Learning with restricted focus of attention, On the Evolution of Monotone Conjunctions: Drilling for Best Approximations, Approximating hyper-rectangles: Learning and pseudorandom sets, Noise-tolerant parallel learning of geometric concepts, Algorithmic Stability for Adaptive Data Analysis, Learning with queries corrupted by classification noise, Hardness of learning problems over Burnside groups of exponent 3, PAC learning with nasty noise., Learning fixed-dimension linear thresholds from fragmented data, Learning from positive and unlabeled examples, Real-valued multiple-instance learning with queries