Robust domain adaptation

We derive a generalization bound for domain adaptation by using the properties of robust algorithms. Our new bound depends on λ-shift, a measure of prior knowledge regarding the similarity of source and target domain distributions. Based on the generalization bound, we design SVM variants for binary classification and regression domain adaptation algorithms.

[1]  Shie Mannor,et al.  Robustness and generalization , 2010, Machine Learning.

[2]  Ameet Talwalkar,et al.  Foundations of Machine Learning , 2012, Adaptive computation and machine learning.

[3]  Koby Crammer,et al.  Analysis of Representations for Domain Adaptation , 2006, NIPS.

[4]  Leslie G. Valiant,et al.  A theory of the learnable , 1984, STOC '84.

[5]  Yishay Mansour,et al.  Learning and Domain Adaptation , 2009, Discovery Science.

[6]  Tyler Lu,et al.  Impossibility Theorems for Domain Adaptation , 2010, AISTATS.

[7]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[8]  Shai Ben-David,et al.  On the Hardness of Domain Adaptation and the Utility of Unlabeled Target Samples , 2012, ALT.

[9]  Yishay Mansour,et al.  Multiple Source Adaptation and the Rényi Divergence , 2009, UAI.

[10]  Mehryar Mohri,et al.  Domain Adaptation in Regression , 2011, ALT.

[11]  John Blitzer,et al.  Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification , 2007, ACL.

[12]  John Blitzer,et al.  Co-Training for Domain Adaptation , 2011, NIPS.

[13]  Shie Mannor,et al.  A distributional interpretation of robust optimization , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[14]  Koby Crammer,et al.  Learning Bounds for Domain Adaptation , 2007, NIPS.

[15]  Yishay Mansour,et al.  Domain Adaptation: Learning Bounds and Algorithms , 2009, COLT.

[16]  Koby Crammer,et al.  A theory of learning from different domains , 2010, Machine Learning.