We further develop the idea that the PAC-Bayes prior can be informed by the data-generating distribution. We prove sharp bounds for an existing framework of Gibbs algorithms, and ...
Uniform random sample is often useful in analyzing data. Usually taking a uniform sample is not a problem if the entire data resides in one location. However, if the data is distr...
Jensen's inequality is a powerful mathematical tool and one of the workhorses in statistical learning. Its applications therein include the EM algorithm, Bayesian estimation ...
The traditional algorithm of Stockmeyer for area minimization of slicing
oorplans has time (and space) complexity O(n2 ) in the worst case, or O(nlogn) for balanced slicing. For ...
CSP search algorithms are exponential in the worst-case. A trivial upper bound on the time complexity of CSP search algorithms is O∗ (dn ), where n and d are the number of variab...