Picture for Yi-Shan Wu

Yi-Shan Wu

Exploring Pessimism and Optimism Dynamics in Deep Reinforcement Learning

Add code
Jun 06, 2024
Viaarxiv icon

Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss

Add code
May 23, 2024
Viaarxiv icon

Probabilistic Actor-Critic: Learning to Explore with PAC-Bayes Uncertainty

Add code
Feb 05, 2024
Viaarxiv icon

If there is no underfitting, there is no Cold Posterior Effect

Add code
Oct 02, 2023
Viaarxiv icon

Split-kl and PAC-Bayes-split-kl Inequalities

Add code
Jun 01, 2022
Figure 1 for Split-kl and PAC-Bayes-split-kl Inequalities
Figure 2 for Split-kl and PAC-Bayes-split-kl Inequalities
Figure 3 for Split-kl and PAC-Bayes-split-kl Inequalities
Figure 4 for Split-kl and PAC-Bayes-split-kl Inequalities
Viaarxiv icon

Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote

Add code
Jun 25, 2021
Figure 1 for Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Figure 2 for Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Figure 3 for Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Figure 4 for Chebyshev-Cantelli PAC-Bayes-Bennett Inequality for the Weighted Majority Vote
Viaarxiv icon