We consider a bandit problem which involves sequential sampling from two populations (arms). Each arm produces a noisy reward realization which depends on an observable random cov...
- In the general case of non-uniformly spaced frequency domain data and/or arbitrarily colored disturbing noise, the frequency domain subspace identification algorithms described i...
Bandit algorithms are concerned with trading exploration with exploitation where a number of options are available but we can only learn their quality by experimenting with them. ...
Stationarity is often an unrealistic prior assumption for Gaussian process regression. One solution is to predefine an explicit nonstationary covariance function, but such covaria...
We develop a penalized kernel smoothing method for the problem of selecting nonzero elements of the conditional precision matrix, known as conditional covariance selection. This p...