In this work, we improve on existing work that studied the relationship between the proof system of modern SAT solvers and general resolution. Previous contributions such as those ...
We study online learnability of a wide class of problems, extending the results of [26] to general notions of performance measure well beyond external regret. Our framework simult...
Alexander Rakhlin, Karthik Sridharan, Ambuj Tewari
We propose a new maximum margin discriminative learning algorithm here for classification of temporal signals. It is superior to conventional HMM in the sense that it does not nee...
Eligibility traces have been shown to speed reinforcement learning, to make it more robust to hidden states, and to provide a link between Monte Carlo and temporal-difference meth...
Doina Precup, Richard S. Sutton, Satinder P. Singh
Evaluating user preferences of web search results is crucial for search engine development, deployment, and maintenance. We present a real-world study of modeling the behavior of ...
Eugene Agichtein, Eric Brill, Susan T. Dumais, Rob...