On Aug 27, 7:35 pm, Bruno Marchal <marc...@ulb.ac.be> wrote:
> Zermelo Fraenkel theory has full transfinite induction power, but is
> still limited by Gödel's incompleteness. What Gentzen showed is that
> you can prove the consistency of ARITHMETIC by a transfinite induction
> up to epsilon_0. This shows only that transfinite induction up to
> epsilon_0 cannot be done in arithmetic.
Yes. That's all I need for the purposes of my criticism of Bayes.
SInce ZF theory has full transfinite induction power, it is more
powerful than arithmetic.
The analogy I was suggesting was:
Arithmetic = Bayesian Inference
Set Theory =Analogical Reasoning
If the above match-up is valid, from the above (Set/Category more
powerful than Arithmetic), it follows that analogical reasoning is
more powerful than Bayesian Inference, and Bayes cannot be the
foundation of rationality as many logicians claim.
The above match-up is justified by (Brown, Porter), who shows that
there's a close match-up between analogical reasoning and Category
‘"Category Theory: an abstract setting for analogy and
comparison" (Brown, Porter)
‘Comparison’ and ‘Analogy’ are fundamental aspects of knowledge
We argue that one of the reasons for the usefulness and importance
of Category Theory is that it gives an abstract mathematical setting
for analogy and comparison, allowing an analysis of the process of
and relating new concepts.’
This shows that analogical reasoning is the deepest possible form of
reasoning, and goes beyond Bayes.
> I agree with your critics on Bayesianism, because it is a good tool
> but not a panacea, and it does not work for the sort of credibility
> measure we need in artificial intelligence.
The problem of priors in Bayesian inference is devastating. Simple
priors only work for simple problems, and complexity priors are
uncomputable. The deeper problem of different models cannot be
solved by Bayesian inference at all:
"One of the most criticized issues in the Bayesian approach is related
priors. Even if there is a consensus on the use of probability
update beliefs, wildly different conclusions can be arrived at from
states of prior beliefs. While such differences tend to diminish with
ing amount of observed data, they are a problem in real situations
the amount of data is always finite. Further, it is only true that
beliefs eventually coincide if everyone uses the same set of models
prior distributions are mutually continuous, i.e., assign non-zero
ties to the same subsets of the parameter space (‘Cromwell’s rule’,
these conditions are very similar to those guaranteeing consistency
As an interesting sidenote, a Bayesian will always be sure that her
predictions are ‘well-calibrated’, i.e., that empirical frequencies
converge to predicted probabilities, no matter how poorly they may
performed so far .
It is actually somewhat misleading to speak of the aforementioned
icism as the ‘problem of priors’, as it were, since what is meant is
least as much a ‘problem of models’: if a different set of models is
differences in beliefs never vanish even with the amount of data going
You received this message because you are subscribed to the Google Groups
"Everything List" group.
To post to this group, send email to email@example.com
To unsubscribe from this group, send email to
For more options, visit this group at