Computer Chess Club Archives


Search

Terms

Messages

Subject: Re: The law of diminishing returns

Author: José Carlos

Date: 01:57:21 07/14/02

Go up one level in this thread


On July 14, 2002 at 01:38:40, Uri Blass wrote:

>On July 13, 2002 at 19:05:35, José Carlos wrote:
>
>>On July 13, 2002 at 17:16:05, Rolf Tueschen wrote:
>>
>>>On July 13, 2002 at 16:57:51, José Carlos wrote:
>>>
>>>>On July 13, 2002 at 15:09:18, Rolf Tueschen wrote:
>>>>
>>>>>On July 13, 2002 at 08:02:09, José Carlos wrote:
>>>>>
>>>>>>On July 13, 2002 at 07:15:53, Rolf Tueschen wrote:
>>>>>>
>>>>>>>On July 13, 2002 at 07:09:02, José Carlos wrote:
>>>>>>>
>>>>>>>>On July 13, 2002 at 05:35:24, Uri Blass wrote:
>>>>>>>>
>>>>>>>>>On July 12, 2002 at 19:16:31, José Carlos wrote:
>>>>>>>>>
>>>>>>>>>>On July 12, 2002 at 14:56:11, Ed Schröder wrote:
>>>>>>>>>>
>>>>>>>>>>>Hi CCC,
>>>>>>>>>>>
>>>>>>>>>>>In Rebel I maintain a statistic file, on every iteration a counter is
>>>>>>>>>>>incremented with 1 (see column 2) representing the iteration depths Rebel has
>>>>>>>>>>>searched. When a new best move is found a second counter is incremented with 1
>>>>>>>>>>>(see column 3) representing how many times a new best move has been found on the
>>>>>>>>>>>given iteration depth, between brackets the percentage is calculated.
>>>>>>>>>>>
>>>>>>>>>>>As you can see the very first plies Rebel often changes to new best moves,
>>>>>>>>>>>however when the depth increases and increases the chance Rebel will change its
>>>>>>>>>>>mind drops and drops. From 16 plies on the chance a new better move is found is
>>>>>>>>>>>below 2%.
>>>>>>>>>>>
>>>>>>>>>>>I wonder what this all means, it is still said (and believed by many) that a
>>>>>>>>>>>doubling in computer speed gives 30-50-70 elo. That could be very well true for
>>>>>>>>>>>lower depths but the below statistic seem to imply something totally different,
>>>>>>>>>>>a sharp diminishing return on deeper depths.
>>>>>>>>>>>
>>>>>>>>>>>Interesting also is colum 4 (Big Score Changes), whenever a big score difference
>>>>>>>>>>>is measured (0.50 up or down) the percentage is calculated. This item seems to
>>>>>>>>>>>be less sensitive than the change in best move. However the maintained "Big
>>>>>>>>>>>Score Changes" statistic is not fully reliable as it also counts situations like
>>>>>>>>>>>being a rook or queen up (or down) in positions and naturally you get (too) many
>>>>>>>>>>>big score fluctuations. I have changed that and have limit the system to scores
>>>>>>>>>>>in the range of -2.50 / +2.50 but for the moment have too few games played to
>>>>>>>>>>>show the new statistic.
>>>>>>>>>>>
>>>>>>>>>>>Anyway the number of positions calculated seem to be more than sufficient (over
>>>>>>>>>>>100,000) to be reliable. The origin came from extensive testing the latest Rebel
>>>>>>>>>>>via self-play at various time controls.
>>>>>>>>>>
>>>>>>>>>>  Hi Ed, if I get this right, the second column (moves searched) is the number
>>>>>>>>>>of positions in which the program has reached the depth given by column 1. If it
>>>>>>>>>>was really "moves", there would be about 3x in depth 2 than in depth 1.
>>>>>>>>>>  Then the idea is that many more changes happen in low depths because the
>>>>>>>>>>program is there many more times, so I (ignoring "Big Changes") calculated a
>>>>>>>>>>couple of other numbers:
>>>>>>>>>>  The ratio moves changes / moves searched and the relative % of changes from
>>>>>>>>>>ply to ply:
>>>>>>>>>>
>>>>>>>>>>                 SEARCH OVERVIEW
>>>>>>>>>>                 ===============
>>>>>>>>>>
>>>>>>>>>>  (A)     (B)            (C)           (D)             (E)
>>>>>>>>>>Depth    Moves          Moves     Moves Changed /   rel % of changes from
>>>>>>>>>>       Searched        Changed    Moves Searched    ply n-1 to n
>>>>>>>>>>
>>>>>>>>>> 1     113768         0 =  0.0%        0
>>>>>>>>>> 2     113768     44241 = 38.9%    0.388870333
>>>>>>>>>> 3     113768     34262 = 30.1%    0.30115674        77.44%
>>>>>>>>>> 4     113194     32619 = 28.8%    0.288168984       95.69%
>>>>>>>>>> 5     113191     30697 = 27.1%    0.271196473       94.11%
>>>>>>>>>> 6     108633     28516 = 26.2%    0.262498504       96.79%
>>>>>>>>>> 7     108180     25437 = 23.5%    0.235135885       89.58%
>>>>>>>>>> 8     102782     22417 = 21.8%    0.218102391       92.76%
>>>>>>>>>> 9      82629     15400 = 18.6%    0.186375244       85.45%
>>>>>>>>>>10      59032      9144 = 15.5%    0.154899038       83.11%
>>>>>>>>>>11      39340      5183 = 13.2%    0.131748856       85.05%
>>>>>>>>>>12      23496      2350 = 10.0%    0.100017024       75.91%
>>>>>>>>>>13      12692       957 =  7.5%    0.075401828       75.39%
>>>>>>>>>>14       6911       396 =  5.7%    0.057299957       75.99%
>>>>>>>>>>15       4032       193 =  4.8%    0.047867063       83.54%
>>>>>>>>>>16       2471        72 =  2.9%    0.029138001       60.87%
>>>>>>>>>>17       1608        26 =  1.6%    0.016169154       55.49%
>>>>>>>>>>18       1138        17 =  1.5%    0.014938489       92.39%
>>>>>>>>>>19        921         6 =  0.7%    0.006514658       43.61%
>>>>>>>>>>20        795         7 =  0.9%    0.008805031      135.16%
>>>>>>>>>>21        711         1 =  0.1%    0.00140647        15.97%
>>>>>>>>>>22        636         2 =  0.3%    0.003144654      223.58%
>>>>>>>>>>23        574         5 =  0.9%    0.008710801      277.00%
>>>>>>>>>>24        507         1 =  0.2%    0.001972387       22.64%
>>>>>>>>>>25        451         3 =  0.7%    0.006651885      337.25%
>>>>>>>>>>26        394         1 =  0.3%    0.002538071       38.16%
>>>>>>>>>>27        343         2 =  0.6%    0.005830904      229.74%
>>>>>>>>>>28        296         2 =  0.7%    0.006756757      115.88%
>>>>>>>>>>29        269         0 =  0.0%    0                  0.00%
>>>>>>>>>>
>>>>>>>>>>  Column (D) means the probability at a certain position at a certain depth to
>>>>>>>>>>get a change, according to your data, for a random position (I assume you chose
>>>>>>>>>>random positions, because this data comes from real games).
>>>>>>>>>
>>>>>>>>>No
>>>>>>>>>
>>>>>>>>>I assume that the positions that was searched to big depthes like 16 are only
>>>>>>>>>positions that the program had enough time to search in the game to depth 16.
>>>>>>>>>
>>>>>>>>>These positions are not random positions from games.
>>>>>>>>>I expect in random positions from games to see at least 10% changes at depth 16.
>>>>>>>>>
>>>>>>>>>Uri
>>>>>>>>
>>>>>>>>  It's interesting that Ed, who has been doing chess programming for a lot of
>>>>>>>>years rely on statistical data, and you, absolute newbie to chess programming
>>>>>>>>can 'expect'. Quite amazing.
>>>>>>>>
>>>>>>>>  José C.
>>>>>>>
>>>>>>>Very telling about your lack of knowledge about interdisciplinary thinking.
>>>>>>>
>>>>>>>Rolf Tueschen
>>>>>>
>>>>>>  Well, you needed several hundred posts from Dann to understand the simple
>>>>>>concept of elo ratings. Lack of knowledge is easy to solve, while lack of
>>>>>>intelligence is a real problem.
>>>>>>  BTW, interdisciplinary thinking has nothing to do with validating intuitions
>>>>>>through experiments.
>>>>>>
>>>>>>  José C.
>>>>>
>>>>>Your habits are a bit strange for CCC. You want to insult people for their
>>>>>intelligence? Didn't you know that this is out of fashion?
>>>>
>>>>  Did you feel insulted? Oh, sorry, I didn't insult you, really.
>>>>
>>>>>Also you cannot prove
>>>>>your visions.
>>>>
>>>>  Visions? I don't have visions. Maybe you take me for someone else ?!
>>>>
>>>>>But I can prove where you lack of knowledge. Look at this:
>>>>>
>>>>>How do you know if or when I understood Elo system? Dann didn't
>>>>>explain anything to _me_,
>>>>
>>>>  Don't feel bad because Dann had to explain that to you. It can happen to
>>>>everybody.
>>>>
>>>>>He was the only one having the courage to give his verdict about SSDF
>>>>>Elo system - _with_ me! We two the only ones. And you were dreaming of his role
>>>>>as _my_ teacher? That's funny.
>>>>
>>>>  I'm glad you enjoied Dann's lessons. Dann is very good at that. I also always
>>>>enjoy his posts.
>>>>
>>>>>You do not  understand what validity means... ;-)
>>>>
>>>>  Good argument!
>>>>
>>>>>You have no idea of what interdisciplinary means too.
>>>>
>>>>  Damn, you leave me without words!
>>>>
>>>>>You are the typical expert
>>>>>with narrow views.
>>>>
>>>>  Thanks for calling me expert... bah, just a little degree in computer science
>>>>and a few publications don't make me an expert...
>>>>
>>>>>Do not insult Uri.
>>>>
>>>>  I didn't. He knows it.
>>>>  BTW, do you feel the need to defend him? Don't you think he is capable to
>>>>defend himself? I think it's you who is insulting Uri.
>>>>
>>>>>Because he knows a lot about chess.
>>>>
>>>>  The first thing where we agree! Cheers!
>>>>
>>>>>Know
>>>>>what I mean? Chess is the basis for computerchess. :)
>>>>
>>>>  Words of wisdom...
>>>>
>>>>>Only interdisciplinary help could enlighten you. If you have questions, please
>>>>>tell me, I'll try to do my best for you.
>>>>>
>>>>>Rolf Tueschen
>>>>
>>>>  Thank you very much. I'll ask you anything I don't understand.
>>>>
>>>>  José C.
>>>
>>>No reason to become so upset only because I told you not to insult Uri.
>>>You have insulted him on his lack of intelligence
>>
>>  Uri knows I didn't. It seems _you_ are not capable to understand. I'm sorry,
>>I'm not gonna explain _you_ what I said to Uri. He understood. That's enough.
>>Please, stop defending him from nothing.
>
>You did not insult me for lack of intelligence but you said that you find it
>strange that I disagree with Ed when Ed has a lot of experience about chess
>programming and I am new in the task of chess programming.
>
>I think that the fact that I am new in chess programming was not relevant for
>the discussion because I do not need to be a programmer to have an opinion about
>data that everyone can see after hours of analyzing.
>
>I doubt if Ed has more experience than me in giving programs hours to analyze
>and looking if the program changes it's mind.
>
>The data that Ed gave is from games and if programs can get depth 16
>in games then the position is relatively simple so the program usually does not
>change it's mind.
>
>Note that I believe in diminishing returns but I still expect significant gain
>from hardare in the near future.
>
>I believe that the difference in comp-comp games at 24 hours per move may be
>only 40 elo from doubling the speed and not 70 elo but 40 elo is still
>significant.
>
>Uri

  My comment was about you "expecting" where Ed was providing experimental data,
nothing more nothing less. Then I asked you for data, you posted some logs and I
find them interesting. That's all. Rolf just invented some nonsense to create
mess. That's his style.

  José C.



This page took 0.01 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.