Yousuke Takada

First, please note that Figure 10.2 compares variational Bayes vs. expectation propagation (moment matching) or minimizing KL(q||p) vs. KL(p||q), and that the solutions have different properties as shown in the...

Thank you very much for your comment. I have a posterior distribution in mind. What I have tried to say in the corresponding errata item is that we can think...

You were right; I am talking about a very broad prior (i.e., the precision $\alpha$ is very small). If combined with a very narrow conditional over the target (i.e., the...

Thank you again for your very helpful comment and I am very glad to hear that you have found my errata "awesome"! As you suggested, I would like to make...

Your point perfectly makes sense! However, since we do not know the true probability distribution in general, we must be careful about the distribution with which we take expectation. So...

Since I require more revisions, I am now working in PR #12. Some more thoughts: * The Bayes free energy F_N and the generalization loss G_N, as defined above, are...

As I said, the terminology here is due to Watanabe (2010, 2013). (The notation is slightly different, though.) I think much of such connections can be found therein. Another book...

A quote from Section 28 "Model Comparison and Occam's Razor" of MacKay (2003) [I have adapted the notation to match the one I introduced above]: > *On-line learning and cross-validation.*...

Thank you for your errata. As for the one for Figure 5.11 on Page 260, I don't see the error you have pointed out. The all sub-figure titles are already...

Thank you for your confirmation. I think we have found another regression error in Figure 5.11. As for Figure 7.1, I agree with you in that we should take the...