Transfer Learning by Distribution Matching for Targeted Advertising

By Steffen Bickel, Christoph Sawade, Tobias Scheffer. 2008

39 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Selective Experience Replay for Lifelong Learning (2018, background): “We can seek to select experiences that match the distribution of all tasks (Bickel, Sawade, and Scheffer 2009), or, given that the future test distribution may differ from the training distribution, we can look to optimize coverage of the state space.”
Feature-based transfer learning with real-world applications (2010, background): “, [219, 107, 49, 48, 87, 82, 21, 180, 67, 20, 148, 22, 147] for example), which assumes that certain parts of the data in the source domain can be reused for learning in the target domain by re-weighting.”
Learning Transferable Knowledge Through Embedding Spaces (2019, methodology): “This can be accomplished with distribution matching [164], inter-task mapping [178], or manifold alignment techniques [179; 180].”
Domain adaptation from multiple sources via auxiliary classifiers (2009, methodology): “In such an extreme case, several domain adaptation methods (Huang et al., 2006; Storkey & Sugiyama, 2006; Sugiyama et al., 2007; Bickel et al., 2008) were proposed to cope with the inconsistency of data distribution (such as covariate shift (Storkey & Sugiyama, 2006) or sampling selection bias (Huan”
Data Science of the People , for the People , by the People : A Viewpoint on an Emerging Dichotomy (2015, background): “We recently studied a Type A problem of predicting health care costs of people in a market that a provider does not serve, which required us to use importance sampling to account for covariate shift [56]; a very similar problem occurs in the Type B problem of targeted advertising [11].”
Multi-domain learning by confidence-weighted parameter combination (2010, background): “Similarly, Bickel et al. (2009) assume a change in prior over examples and derive a procedure for resampling weights that match the available examples to ones in the target domain.”
Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfer (2017, methodology): “TL and MTL techniques typically select the relevant knowledge to transfer by modeling inter-task relationships using a shared representation, based on training data for each task (Baxter, 2000; Ando & Zhang, 2005; Bickel, Sawade, & Scheﬀer, 2009; Maurer, Pontil, & Romera-Paredes, 2013).”