Multi-View Active Learning in the Non-Realizable Case
نویسندگان
چکیده
The sample complexity of active learning under the realizability assumption has been well-studied. The realizability assumption, however, rarely holds in practice. In this paper, we theoretically characterize the sample complexity of active learning in the non-realizable case under multiview setting. We prove that, with unbounded Tsybakov noise, the sample complexity of multiview active learning can be Õ(log 1ǫ ), contrasting to single-view setting where the polynomial improvement 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 previous polynomial bounds where the order of 1/ǫ is related to the parameter in Tsybakov noise.
منابع مشابه
Active Learning in the Non-realizable Case
Most of the existing active learning algorithms are based on the realizability assumption: The learner’s hypothesis class is assumed to contain a target function that perfectly classifies all training and test examples. This assumption can hardly ever be justified in practice. In this paper, we study how relaxing the realizability assumption affects the sample complexity of active learning. Fir...
متن کاملOnline Passive-Aggressive Algorithms
We present a unified view for online classification, regression, and uniclass problems. This view leads to a single algorithmic framework for the three problems. We prove worst case loss bounds for various algorithms for both the realizable case and the non-realizable case. A conversion of our main online algorithm to the setting of batch learning is also discussed. The end result is new algori...
متن کاملActive Learning via Perfect Selective Classification
We discover a strong relation between two known learning models: stream-based active learning and perfect selective classification (an extreme case of ‘classification with a reject option’). For these models, restricted to the realizable case, we show a reduction of active learning to selective classification that preserves fast rates. Applying this reduction to recent results for selective cla...
متن کاملActive Learning of Halfspaces
We study pool-based active learning of half-spaces. In this setting a learner receives a pool of unlabeled examples, and can iteratively query a teacher for the labels of examples from the pool. The goal of the learner is to return a low-error prediction rule for the labels of the examples, using a small number of queries. Most active learning approaches can be loosely described as more ‘aggres...
متن کاملEfficient Active Learning of Halfspaces: an Aggressive Approach
We study pool-based active learning of halfspaces. We revisit the aggressive approach for active learning in the realizable case, and show that it can be made efficient and practical, while also having theoretical guarantees under reasonable assumptions. We further show, both theoretically and experimentally, that it can be preferable to mellow approaches. Our efficient aggressive active learne...
متن کامل