PAC-Learning with General Class Noise Models
نویسندگان
چکیده
We introduce a framework for class noise, in which most of the known class noise models for the PAC setting can be formulated. Within this framework, we study properties of noise models that enable learning of concept classes of finite VC-dimension with the Empirical Risk Minimization (ERM) strategy. We introduce simple noise models for which classical ERM is not successful. Aiming at a more generalpurpose algorithm for learning under noise, we generalize ERM to a more powerful strategy. Finally, we study general characteristics of noise models that enable learning of concept classes of finite VC-dimension with this new strategy.
منابع مشابه
On the Sample Complexity of Noise-Tolerant Learning
In this paper, we further characterize the complexity of noise-tolerant learning in the PAC model. Specifically, we show a general lower bound of Ω ( log(1/δ) ε(1−2η) ) on the number of examples required for PAC learning in the presence of classification noise. Combined with a result of Simon, we effectively show that the sample complexity of PAC learning in the presence of classification noise...
متن کاملGeneral Bounds on Statistical Query Learning and PAC Learning with Noise via Hypothesis Bounding
We derive general bounds on the complexity of learning in the Statistical Query model and in the PAC model with classification noise. We do so by considering the problem of boosting the accuracy of weak learning algorithms which fall within the Statistical Query model. This new model was introduced by Kearns [12] to provide a general framework for efficient PAC learning in the presence of class...
متن کاملSample-eecient Strategies for Learning in the Presence of Noise
In this paper we prove various results about PAC learning in the presence of malicious noise. Our main interest is the sample size behaviour of learning algorithms. We prove the rst nontrivial sample complexity lower bound in this model by showing that order of "= 2 + d= (up to logarithmic factors) examples are necessary for PAC learning any target class of f0; 1g-valued functions of VC dimensi...
متن کاملFour Types of Noise in Data for PAC Learning
In order to be useful in practice, machine learning algorithms must tolerate noisy inputs. In this paper we compare and contrast the effects of four different types of noise on learning in Valiant’s PAC (probably approximately correct), or distribution-free, model of learning [ 111. Two previously studied models, malicious noise [ 121 and random classification noise [ 11, represent the extremes...
متن کاملActive and passive learning of linear separators under log-concave distributions
We provide new results concerning label efficient, polynomial time, passive and active learning of linear separators. We prove that active learning provides an exponential improvement over PAC (passive) learning of homogeneous linear separators under nearly log-concave distributions. Building on this, we provide a computationally efficient PAC algorithm with optimal (up to a constant factor) sa...
متن کامل