@inproceedings{raman_etal_13a,
   url = {http://jmlr.org/proceedings/papers/v28/raman13.pdf}, 
   booktitle = {Proceedings of the 30th International Conference on Machine Learning (ICML-13)}, 
   series = {ICML-13},
   editor = {Sanjoy Dasgupta and David McAllester}, 
   publisher = {JMLR Workshop and Conference Proceedings}, 
   volume = {28}, 
   number = {3}, 
   month = {May}, 
   year = {2013}, 
   title = {Stable Coactive Learning via Perturbation}, 
   author = {Raman, Karthik and Joachims, Thorsten and Shivaswamy, Pannaga and Schnabel, Tobias}, 
   pages = {837-845}, 
   abstract = {Coactive Learning is a model of interaction between a learning system (e.g. search engine) and its human users, wherein the system learns from (typically implicit) user feedback during operational use. User feedback takes the form of preferences, and recent work has introduced online algorithms that learn from this weak feedback. However, we show that these algorithms can be unstable and ineffective in real-world settings where biases and noise in the feedback are significant. In this paper, we propose the first coactive learning algorithm that can learn robustly despite bias and noise. In particular, we explore how presenting users with slightly perturbed objects (e.g., rankings) can stabilize the learning process. We theoretically validate the algorithm by proving bounds on the average regret. We also provide extensive empirical evidence on benchmarks and from a live search engine user study, showing that the new algorithm substantially outperforms existing methods.} 
   }