On the Version Space Compression Set Size and Its Applications

The version space compression set size n is the size of the smallest subset of a training set that induces the same (agnostic) version space with respect to a hypothesis class.

[1]  Ran El-Yaniv,et al.  Active Learning via Perfect Selective Classification , 2012, J. Mach. Learn. Res..

[2]  Steve Hanneke,et al.  Theoretical foundations of active learning , 2009 .

[3]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[4]  Steve Hanneke,et al.  Teaching Dimension and the Complexity of Active Learning , 2007, COLT.

[5]  David A. Cohn,et al.  Improving generalization with active learning , 1994, Machine Learning.

[6]  Ran El-Yaniv,et al.  Agnostic Selective Classification , 2011, NIPS.

[7]  M. Narasimha Murty,et al.  A fast linear separability test by projection of positive points on subspaces , 2007, ICML '07.

[8]  Ran El-Yaniv,et al.  On the Foundations of Noise-free Selective Classification , 2010, J. Mach. Learn. Res..

[9]  H. T. Kung,et al.  On the Average Number of Maxima in a Set of Vectors and Applications , 1978, JACM.

[10]  Steve Hanneke,et al.  Activized Learning: Transforming Passive to Active with Improved Label Complexity , 2011, J. Mach. Learn. Res..

[11]  Ralf Herbrich,et al.  Learning Kernel Classifiers , 2001 .

[12]  Ran El-Yaniv,et al.  Agnostic Pointwise-Competitive Selective Classification , 2015, J. Artif. Intell. Res..

[13]  Tom M. Mitchell,et al.  Version Spaces: A Candidate Elimination Approach to Rule Learning , 1977, IJCAI.

[14]  Vladimir Vapnik,et al.  Chervonenkis: On the uniform convergence of relative frequencies of events to their probabilities , 1971 .

[15]  Steve Hanneke,et al.  A bound on the label complexity of agnostic active learning , 2007, ICML '07.

[16]  Ran El-Yaniv,et al.  Pointwise Tracking the Optimal Regression Function , 2012, NIPS.

[17]  Manfred K. Warmuth,et al.  Relating Data Compression and Learnability , 2003 .