It has been widely recognized that the dynamic range information of an application can be exploited to reduce the datapath bitwidth of either processors or ASICs, and therefore th...
We examine the problem of evaluating a policy in the contextual bandit setting using only observations collected during the execution of another policy. We show that policy evalua...
John Langford, Alexander L. Strehl, Jennifer Wortm...
We design a linear time approximation scheme for the GaleBerlekamp Switching Game and generalize it to a wider class of dense fragile minimization problems including the Nearest C...
Characterising the differences between two databases is an often occurring problem in Data Mining. Detection of change over time is a prime example, comparing databases from two b...
Past empirical work has shown that learning multiple related tasks from data simultaneously can be advantageous in terms of predictive performance relative to learning these tasks...