We present a general Bayesian framework for hyperparameter tuning in L2-regularized supervised learning models. Paradoxically, our algorithm works by first analytically integratin...
We consider the problem of multi-task reinforcement learning, where the agent needs to solve a sequence of Markov Decision Processes (MDPs) chosen randomly from a fixed but unknow...
Aaron Wilson, Alan Fern, Soumya Ray, Prasad Tadepa...
We introduce a new model for learning with membership queries in which queries near the boundary of a target concept may receive incorrect or “don’t care” responses. In part...
Avrim Blum, Prasad Chalasani, Sally A. Goldman, Do...
Discriminative learning techniques for sequential data have proven to be more effective than generative models for named entity recognition, information extraction, and other task...
Interaction analysis within online educational contexts based on collaborative learning strategies requires a multidimensional model taking into account social, emotional and cogni...