Search Results for author:
Found 5 papers, 2 papers with code
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
While PAC-Bayes allows construction of data-informed priors, the final confidence intervals depend only on the number of points that were not used for the construction of the prior, whereas confidence information in the prior, which is related to the number of points used to construct the prior, is lost.
Probabilistic Actor-Critic: Learning to Explore with PAC-Bayes Uncertainty
We introduce Probabilistic Actor-Critic (PAC), a novel reinforcement learning algorithm with improved continuous control performance thanks to its ability to mitigate the exploration-exploitation trade-off.
If there is no underfitting, there is no Cold Posterior Effect
The cold posterior effect (CPE) (Wenzel et al., 2020) in Bayesian deep learning shows that, for posteriors with a temperature $T<1$, the resulting posterior predictive could have better performances than the Bayesian posterior ($T=1$).
Split-kl and PAC-Bayes-split-kl Inequalities for Ternary Random Variables
We present a new concentration of measure inequality for sums of independent bounded random variables, which we name a split-kl inequality.
Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
The bound is based on a novel parametric form of the Chebyshev- Cantelli inequality (a. k. a.
