On a Method of Empirical Risk Minimization
Problems of Information Transmission
Information Theory and Mixing Least-Squares Regressions
IEEE Transactions on Information Theory
Hi-index | 0.00 |
We consider the problem of recovering an unknown vector from noisy data. The vector is estimated using a family of projection estimates, and the goal is finding a sufficiently good convex combination of these estimates based on the observations. We study an aggregation method for constructing estimates related to the so-called exponential weighting and present an upper bound on the mean-square risk of this method.