no code implementations • 14 Aug 2020 • Puja Sahu, Nandyala Hemachandra
We investigate optimal posteriors for recently introduced \cite{begin2016pac} chi-squared divergence based PAC-Bayesian bounds in terms of nature of their distribution, scalability of computations, and test set performance.
no code implementations • 14 Dec 2019 • Puja Sahu, Nandyala Hemachandra
This obviates the combinatorial search for subset support of the optimal posterior.