Quantifying the Value of Privileged Information Using a PAC-Bayesian Approach
An algorithm-agnostic, information-theoretic approach based on the PAC-Bayes framework is introduced that quantifies the potential of privileged features before committing to a model, and takes a necessary step toward an information-theoretic understanding of LUPI.
Vasily Bokov, Sebastian Schmitt, V. Dunjko et al.
· 0 citations