Active Learning: Disagreement Coefficient
نویسنده
چکیده
In previous lectures we saw examples in which active learning gives an exponential improvement in the number of labels required for learning. In this lecture we describe the Disagreement Coefficient —a measure of the complexity of an active learning problem proposed by Steve Hanneke in 2007. We will derive an algorithm for the realizable case and analyze it using the disagreement coefficient. In particular, we will show that if the disagreement coefficient is constant then it is possible to obtain exponential improvement over passive learning. We will also describe a variant of the Agnostic Active (A) algorithm (due to Balcan, Beygelzimer, Langford) and show how an exponential improvement can be obtained even in the agnostic case, as long as the accuracy is proportional to the best error rate.
منابع مشابه
Smoothness, Disagreement Coefficient, and the Label Complexity of Agnostic Active Learning
We study pool-based active learning in the presence of noise, that is, the agnostic setting. It is known that the effectiveness of agnostic active learning depends on the learning problem and the hypothesis space. Although there are many cases on which active learning is very useful, it is also easy to construct examples that no active learning algorithm can have an advantage. Previous works ha...
متن کاملActive Learning Using Smooth Relative Regret Approximations with Applications
The disagreement coefficient of Hanneke has become a central concept in proving active learning rates. It has been shown in various ways that a concept class with low complexity together with a bound on the disagreement coefficient at an optimal solution allows active learning rates that are superior to passive learning ones. We present a different tool for pool based active learning which foll...
متن کاملThe Relationship Between Agnostic Selective Classification Active Learning and the Disagreement Coefficient
A selective classifier ( f ,g) comprises a classification function f and a binary selection function g, which determines if the classifier abstains from prediction, or uses f to predict. The classifier is called pointwise-competitive if it classifies each point identically to the best classifier in hindsight (from the same class), whenever it does not abstain. The quality of such a classifier i...
متن کاملLower Bounds for Passive and Active Learning
We develop unified information-theoretic machinery for deriving lower bounds for passive and active learning schemes. Our bounds involve the so-called Alexander’s capacity function. The supremum of this function has been recently rediscovered by Hanneke in the context of active learning under the name of “disagreement coefficient.” For passive learning, our lower bounds match the upper bounds o...
متن کاملActivized Learning: Transforming Passive to Active with Improved Label Complexity∗ Working Notes: Updated January 2011
We study the theoretical advantages of active learning over passive learning. Specifically, we prove that, in noise-free classifier learning for VC classes, any passive learning algorithm can be transformed into an active learning algorithm with asymptotically strictly superior label complexity for all nontrivial target functions and distributions, in many cases without significant loss in comp...
متن کامل