timtyler comments on Metaphilosophical Mysteries - Less Wrong

35 Post author: Wei_Dai 27 July 2010 12:55AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Article Navigation

Comments (255)

Comments (255)

Sort By: Best

Show:

You are viewing a single comment's thread. Show more comments above.

Comment author: timtyler 27 July 2010 07:44:25PM * -1 points [-]

P(true) = 0 - or p(false) = 1 - seem like trivial mistakes to avoid.

A "expected utility maximizer programmed with a TM-based universal prior" would surely not care very much if it was programmed with wrong priors after a while - since it would not be depending on the details of its priors much any more - due to having a big mountain of experience concerning what the actual expected frequency of events was. Its priors would be swamped by data - unless its priors were completely crazy.

The OP must be thinking of some different type of construct from me - and he doesn't seem to explain what it is.

Comment author: cousin_it 27 July 2010 07:52:02PM * 4 points [-]

P(true) = 0 or p(false) = 1 seem like trivial mistakes to avoid.

Unfortunately they aren't. A universal prior must enumerate all the ways a universe could possibly be. If your prior is based on Turing machines that compute universes, but our actual universe is uncomputable, you're screwed forever no matter what data comes in. Maybe the problem can be solved by a better universal prior, as Nesov suggests elsewhere in the thread, but as far as I understand it's an open problem right now.

ETA: pretty much this whole comment is wrong. The prior is over algorithms that generate sequences of sensory input, not over algorithms that define universes. This is an important distinction, sorry for missing it when I wrote this comment.

Comment author: PhilGoetz 27 July 2010 07:56:18PM 0 points [-]

Natural selection solves this problem.

Comment author: SilasBarta 27 July 2010 08:39:52PM 0 points [-]

A universal prior must enumerate all the ways a universe could possibly be. If your prior is based on Turing machines that compute universes, but our actual universe is uncomputable, you're screwed forever no matter what data comes in.

Being forced to use the nearest computable approximation to an uncomputable function does not make you screwed forever.

Comment author: cousin_it 27 July 2010 08:42:01PM * 1 point [-]

That depends on the uncomputable function. Some can make you very well screwed indeed. It's all there in Wei Dai's examples on everything-list and one-logic, I really wish people would read them, maybe we'd have an actual discussion then. Sorry for sounding harsh.

Comment author: SilasBarta 27 July 2010 08:49:08PM * 1 point [-]

That depends on the uncomputable function. Some can make you very well screwed indeed.

Right, but it's not necessarily true, or even likely, hence my point.

It's all there in Wei Dai's examples on everything-list and one-logic, I really wish people would read them, maybe we'd have an actual discussion then.

I did read the links, (including the link to the empty stub article!), and the google group discussions all seemed to end, from my brief perusing of them, with them coming to the consensus that Wei Dai hadn't established his provacative, counterintuitive point. (And some of the exchanges here show the same.)

At the very least, he should summarize the reasoning or examples, as per standard practice, so we know there's something to be gained from going to the links. This is especially true given that most readers had assumed that the opposite of Wei Dai's premises are true and uncontroversial.

Comment author: timtyler comment score below threshold [+] (64 children)

Comment author: cousin_it 27 July 2010 08:33:22PM 2 points [-]

I'm not sure - did you miss the idea that all "universal priors" that we know how to construct today assign zero credence to certain hypotheses about the universe, or did you miss the idea that a zero-credence hypothesis will never rise above zero no matter how much data comes in, or is it me who's missing something?

Comment author: SilasBarta 28 July 2010 06:14:37PM * 2 points [-]

Also, correct me if I'm wrong, but doesn't the Solomonoff prior bypass the issue of explicit hypotheses? That is, it puts a (non-zero) prior on every (prefix) bitstream of sensory data.

So, it doesn't even seem necessary to talk about what such an agent's "priors on hypotheses" are -- everything it believes is encoded as an expectation of sensory data, and nothing more. It does not explicitly represent concepts like, "this thing is a halting oracle".

Instead, when it encounters a halting oracle, it increases the weight it assigns to expectations of observations of things that are consistent with having been produced by a halting oracle, not the existence of a halting oracle as such.

No matter how uncomputable, or lengthy-to-specify, a function might be, you can always finitely specify your expectation weight on a finite observation prefix stream (i.e. the first n things you observe from the oracle).

So, I don't see how an agent with a Solomonoff prior chokes on an encounter with a halting oracle.

Comment author: timtyler 01 August 2010 01:00:14AM * 0 points [-]

Normal agents won't. Genuinely intelligent agents won't.

I think those who are arguing that it will are imagining an agent with the Solomonoff prior totally wired into them in a manner that they can't possibly unlearn.

Comment author: SilasBarta 01 August 2010 05:15:07AM * 2 points [-]

But still, even if you have the Occamian prior (which I think is what's meant by the Solomonoff prior), there is no need to unlearn it. You retain a prior on all hypotheses that decreases in weight exponentially with length, and it persists on top of any observations you've updated on. Those new observations, combined with the Occamian prior give you the optimal weights on (prefix) sensory bitstreams, discounting the ruled-out ones and favoring those closer to what you've actually observed.

Even then, it keeps updating in favor of the observations that match what an oracle gives (without having to explicitly represent that they're from an oracle). No penalty from failure to unlearn.

Comment author: timtyler 01 August 2010 07:17:04AM * 0 points [-]

The thing is, there is no one true razor. Different sources have different associated reference machines - some are more like Turing Machines, others are more like CA. If what you are looking at is barcodes, then short ones are pretty rare - and if you go into simulated worlds, sources can have practically any distribution you care to mention.

Yes, you can model these as "complier overhead" constants - which represent the "cost" of simulating one reference machine in another - but that is just another way of saying you have to unlearn the Solomonoff prior and use another one - which is more appropriate for your source.

You can still do that, whatever your reference machine is - provided it is computationally universal - and doesn't have too much "faith".

Comment author: NancyLebovitz 28 July 2010 01:08:00AM 0 points [-]

I'm not sure exactly what can qualify as a prior.

Is "Anomalies may be clues about a need to make deep changes in other priors" a possible prior?

Comment author: cousin_it 28 July 2010 03:59:30AM * 1 point [-]

A prior is not a program that tells you what to do with the data. A prior is a set of hypotheses with a number assigned to each. When data comes in, we compute the likelihoods of the data given each hypothesis on the list, and use these numbers to obtain a posterior over the same hypotheses. There's no general way to have a "none of the above" (NOTA) hypothesis in your prior, because you can't compute the likelihood of the data given NOTA.

Another equivalent way to think about it: because of the marginalization step (dividing everything by the sum of all likelihoods), Bayesian updating doesn't use the total likelihood of the data given all current hypotheses - only the relative likelihoods of one hypothesis compared to another. This isn't easy to fix because "total likelihood" is a meaningless number that doesn't indicate anything - it could easily be 1000 in a setup with an incorrect prior or 0.001 in a setup with a correct prior.

Comment author: NancyLebovitz 28 July 2010 09:29:53AM 0 points [-]

People have beliefs about how various sorts of behavior will work out, though I think it's rare to have probabilities attached.

Comment author: timtyler 27 July 2010 09:56:38PM * 0 points [-]

If you are assigning p(some empirical hypothesis) = 0, surely you are a broken system.

Comment author: timtyler 27 July 2010 10:02:12PM * 2 points [-]

The example seems to be that a using a Turing machine to generate your priors somehow results in an expectation of p(uncomputable universe)=0. That idea just seems like total nonsense to me. It just doesn't follow. For all I care, my priors could have been assigned to me using a Turing machine model at birth - but I don't think p(uncomputable universe)=0. The whole line of reasoning apparently makes no sense.

Comment author: cousin_it 28 July 2010 03:56:00AM 1 point [-]

The universal prior enumerates all Turing machines, not all possible priors generated by all Turing machines.

Comment author: timtyler 28 July 2010 07:17:47AM * 0 points [-]

Priors are probabality estimates for uncertain quantities.

In Solomonoff induction they are probabality estimates for bitstrings - which one can think of as representing possible sensory inputs for an agent.

With a standard TM_length-based encoding, no finite bitstring is assigned a zero probability - and we won't have to worry about perceiving infinite bitstrings until after the universal heat death - so there is no problem with assigning certain bitstrings a zero prior probability.

Whether the bitstrings were created using uncomputable physics is neither here nor there. They are still just bitstrings - and so can be output by a TM with a finite program on its tape.

Comment author: cousin_it 28 July 2010 08:26:07AM * 0 points [-]

No, sorry. You're confused. A prior is not an assignment of credences to all bitstrings that you can observe. A prior is an assignment of credences to hypotheses, i.e. possible states of the world that generate bitstrings that you observe. Otherwise you'd find yourself in this text (see part II, "Escaping the Greek Hinterland").

Comment author: timtyler 28 July 2010 08:59:43AM * 2 points [-]

No. We were talking about the universal prior. Here is how that is defined for sequences:

"The universal prior probability of any prefix p of a computable sequence x is the sum of the probabilities of all programs (for a universal computer) that compute something starting with p."

http://en.wikipedia.org/wiki/Inductive_inference

The universal prior of a sequence is the probability of that particular sequence arising (as a prefix). It is not the probabilty of any particular hypothesis or program. Rather is a weighted sum of the probabilities of all the programs that generate that sequence.

You can talk about the probabilities of hypothesis and programs as well if you like - but the universal prior of a sequence is perfectly acceptable subject matter - and is not a "confused" idea.

No finite sequence has a probabilty of zero - according to the universal prior.

All finite bitstrings can be produced by computable means - even if they were generated as the output of an uncomputable physical process.

timtyler comments on Metaphilosophical Mysteries - Less Wrong

Article Navigation

Comments (255)

Nearest Meetups

Virtual Study Room

Recent Comments

Recent Posts

Recent Rationality Quotes

Recent Wiki Edits

Top Contributors, 30 Days

Recent Karma Awards

Comments (255)

Top Contributors, 30 Days

You'll need to login or register to do that

(Don't worry, it only takes a few seconds)

Create

Login