Author: Rolf Tueschen
Date: 02:47:24 01/21/03
Go up one level in this thread
On January 20, 2003 at 21:15:53, Dann Corbit wrote: >On January 20, 2003 at 18:41:02, Sune Fischer wrote: > >>On January 20, 2003 at 18:34:21, Dann Corbit wrote: >> >>>On January 20, 2003 at 18:08:45, Sune Fischer wrote: >>> >>>>On January 20, 2003 at 17:27:44, Dann Corbit wrote: >>>> >>>>>>>No contest can truly tell us which program is strongest. Not even a trillion >>>>>>>rounds of round-robin. >>>>>>I disagree again. I believe a trillion rounds will show which program is >>>>>>strongest. >>>>> >>>>>You're wrong. >>>>> >>>> >>>>No he is right. >>>>There is a saying in statistics (IIRC correctly) "null events don't happen". >>>> >>>>Basicly it means things that are very very improbable are impossible. >>>> >>>>You would never see TSCP beat Fritz more than 50% of the time if you did a >>>>trillion games. No one has done more than a trillion games yet, we all know >>>>fritz is stronger, why is that? ;) >>> >>>Until the number of games reaches infinity, there will always be uncertainty. >>> >>>Because there is some degree of randomness in the programs, I'm not even sure >>>that there *is* an answer to the question: >>>"Which is stronger, Chess Tiger or Fritz?" >>> >>>For programs with hundreds of ELO difference, you can be fairly certain >>>relatively quickly. For programs of about the same strength, you will never >>>know the answer. >> >>But what you were saying was, that you could _never ever_ know the answer. There >>is a fundamental difference I think and this is where the null event theorem >>saves us. It _is_ possible to make an accurate statement if you have reduced it >>to a null event. After 1 trillion games I think we have a clear winner, whom >>ever that may be. > >I would be utterly astonished if it were true. > >After a trillion coin flips, we will still have random walk problems, and it >could (on rare occasions) be considerable. How will we discern the random walk >drift from a very tiny change in strength? At the top, the strength of the >programs appears to be very close. This is the exact region where random walk >will give us the most trouble. > >In other words, I think we will not be able to discern (on a blind test) whether >we pit top program A against top program B or whether it was A against A or B >against B. Didn't follow your debate, but at least here I think we should consider something. It is confusing how you argue. WHY should someone do blind tests IF he wants to know the difference between progs? Ok, you say that the differences are very very small, but I say that in a million games, not to speak of your trillion, I could say who's who. But surely NOT with closed eyes but with looking at the chess. Often in science the solution is so near and you must open your eyes. Staying in abstract discussions could be fatal on the contrary. I think we have a typical case where even highly educated experts could look stupid. But I would prefer the version that here people simply show that they are no experts at all but simply experts in other fields and now they try some steps on their own. It's apparent how blind we are in such a case because we don't discover the most trivial things. Here the one side is talking about chess progs and the other about coin tosses - assuming that the latter almost were the same or at least we could simulate the more compley process in the first case. But no matter if my guess is correct, it's a typical sort of error. Sort of self-blinding and confusing the real situation. Chess seems no question at all. A good anecdote. A drunken man had lost his wedding ring in the night. He's searching for it under the bright light of a streetlamp. He's crawling. Suddenly a policeman arrives and asks what's going on. Moments later the policeman is also crawling on the floor. But then he asks the man, but where did you lose your ring exactly? And the man pointed into some direction in the dark. The policeman was astonished and said, so you don't know exactly that it was here? No, answered the man, but here at least I have a good view. - And the moral out of the story is this: in science you have to search in the dark, if the problem is still in the dark, no matter if you like it or not. But to seek for the solution in certain easy places (=conditions) doesn't help you. Of course it looks always smarter if someone makes analogies and can therefore present easy answers. But it's all depending of the correctness of the analogies. Rolf Tueschen
This page took 0 seconds to execute
Last modified: Thu, 15 Apr 21 08:11:13 -0700
Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.