Communications of the ACM
Learnability and the Vapnik-Chervonenkis dimension
Journal of the ACM (JACM)
Equivalence of models for polynomial learnability
COLT '88 Proceedings of the first annual workshop on Computational learning theory
Tracking drifting concepts using random examples
COLT '91 Proceedings of the fourth annual workshop on Computational learning theory
PREDICTING {0,1}-FUNCTIONS ON RANDOMLY DRAWN POINTS
PREDICTING {0,1}-FUNCTIONS ON RANDOMLY DRAWN POINTS
Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics)
Statistical queries and faulty PAC oracles
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
Fat-shattering and the learnability of real-valued functions
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Exploiting random walks for learning
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
On the complexity of learning from drifting distributions
COLT '96 Proceedings of the ninth annual conference on Computational learning theory
Improved lower bounds for learning from noisy examples: an information-theoretic approach
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
The complexity of learning according to two models of a drifting environment
COLT' 98 Proceedings of the eleventh annual conference on Computational learning theory
The Complexity of Learning According to Two Models of a Drifting Environment
Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Learning Changing Concepts by Exploiting the Structure of Change
Machine Learning
Exploiting random walks for learning
Information and Computation
Distinctive Features of Minimization of a Risk Functional in Mass Data Sets
Cybernetics and Systems Analysis
New analysis and algorithm for learning with drifting distributions
ALT'12 Proceedings of the 23rd international conference on Algorithmic Learning Theory
| Hi-index | 0.00 |
In this paper, we consider the problem of learning a subset of a domain from randomly chosen examples when the probability distribution of the examples changes slowly but continually throughout the learning process. We give upper and lower bounds on the best achievable probability of misclassification after a given number of examples. If d is the VC-dimension of the target function class, t is the number of examples, and &Ugr; is the amount by which the distribution is allowed to change (measured by the largest change in the probability of a subset of the domain), the upper bound decreases as d/t initially, and settles to O(d2/3&Ugr;1/2) for large t. These bounds give necessary and sufficient conditions on &Ugr;, the rate of change of the distribution of examples, to ensure that some learning algorithm can produce an acceptably small probability of misclassification. We also consider the case of learning a near-optimal subset of the domain when the examples and their labels are generated by a joint probability distribution on the example and label spaces. We give an upper bound on &Ugr; that ensures learning is possible from a finite number of examples.