The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in prac-tice. In this paper, we theoretically characterize the sample complexity of active learning in the non-realizable case under multi-view setting. We prove that, with unbounded Tsybakov noise, the sample complexity of multi-view active learning can be Õ(log 1ǫ), contrasting to single-view setting where the polynomial improve-ment is the best possible achievement. We also prove that in general multi-view setting the sample complexity of active learning with unbounded Tsybakov noise is Õ ( 1ǫ), where the order of 1/ǫ is independent of the parameter in Tsybakov noise, contrasting to prev...
AbstractWe state and analyze the first active learning algorithm that finds an ϵ-optimal hypothesis ...
We present an agnostic active learning algorithm for any hypothesis class of bounded VC dimension un...
The goal of active learning is to achieve the same accuracy achievable by passive learning, while us...
The sample complexity of active learning under the realizability assumption has been well-studied. T...
We characterize the sample complexity of active learning problems in terms of a parameter which tak...
<p>We present a polynomial-time noise-robust margin-based active learning algorithm to find homogene...
This paper analyzes the potential advantages and theoretical challenges of "active learning" algorit...
We present a simple noise-robust margin-based active learn-ing algorithm to find homogeneous (passin...
We study pool-based active learning in the presence of noise, that is, the agnostic setting. It is k...
The original and most widely studied PAC model for learning assumes a passive learner in the sense t...
This dissertation develops and analyzes active learning algorithms for binary classification problem...
In many settings in practice it is expensive to obtain labeled data while unlabeled data is abundant...
We study pool-based active learning in the presence of noise, i.e. the agnostic setting. Previous wo...
The original and most widely studied PAC model for learning assumes a passive learner in the sense t...
International audienceActive learning is a branch of Machine Learning in which the learning algorith...
AbstractWe state and analyze the first active learning algorithm that finds an ϵ-optimal hypothesis ...
We present an agnostic active learning algorithm for any hypothesis class of bounded VC dimension un...
The goal of active learning is to achieve the same accuracy achievable by passive learning, while us...
The sample complexity of active learning under the realizability assumption has been well-studied. T...
We characterize the sample complexity of active learning problems in terms of a parameter which tak...
<p>We present a polynomial-time noise-robust margin-based active learning algorithm to find homogene...
This paper analyzes the potential advantages and theoretical challenges of "active learning" algorit...
We present a simple noise-robust margin-based active learn-ing algorithm to find homogeneous (passin...
We study pool-based active learning in the presence of noise, that is, the agnostic setting. It is k...
The original and most widely studied PAC model for learning assumes a passive learner in the sense t...
This dissertation develops and analyzes active learning algorithms for binary classification problem...
In many settings in practice it is expensive to obtain labeled data while unlabeled data is abundant...
We study pool-based active learning in the presence of noise, i.e. the agnostic setting. Previous wo...
The original and most widely studied PAC model for learning assumes a passive learner in the sense t...
International audienceActive learning is a branch of Machine Learning in which the learning algorith...
AbstractWe state and analyze the first active learning algorithm that finds an ϵ-optimal hypothesis ...
We present an agnostic active learning algorithm for any hypothesis class of bounded VC dimension un...
The goal of active learning is to achieve the same accuracy achievable by passive learning, while us...