Sequential optimal design methods hold great promise for improving the efficiency of neurophysiology experiments. However, previous methods for optimal experimental design have in...
Jeremy Lewi, Robert J. Butera, David M. Schneider,...
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
Necessary first-order sequential optimality conditions provide adequate theoretical tools to justify stopping criteria for nonlinear programming solvers. These conditions are sati...
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
The power and popularity of kernel methods stem in part from their ability to handle diverse forms of structured inputs, including vectors, graphs and strings. Recently, several m...
Darrin P. Lewis, Tony Jebara, William Stafford Nob...