That's how far false marketing can go.
Fat Fritz 2 is based on a development version of stockfish from early february this year and is worse than said base.
larger nets for SF?
Moderators: hgm, Rebel, chrisw
-
- Posts: 389
- Joined: Tue Oct 08, 2019 11:39 pm
- Full name: Tomasz Sobczyk
Re: larger nets for SF?
dangi12012 wrote:No one wants to touch anything you have posted. That proves you now have negative reputations since everyone knows already you are a forum troll.
Maybe you copied your stockfish commits from someone else too?
I will look into that.
-
- Posts: 12542
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: larger nets for SF?
It appears that my point was missed entirely.
If you examine the Elo of the LC0 nets, the larger the net, the larger the Elo. And it isn't close. The big nets CLOBBER the smaller ones.
I think that bigger and bigger nets should be constructed until it is no longer true.
Similarly with SF.
Yes, Albert spent a great deal of money testing out his ideas. But the resources he could purchase are not nearly so large as the free resource of the SF mega-team has at their very fingertips.
And yet this upstart beats them all:
http://www.cegt.net/40_40%20Rating%20Li ... liste.html
What did he do?
Well, one OBVIOUS thing is to double the net size.
Now, he also did special analysis to vary the input data, which is not to be discounted.
But why shouldn't the SF team double, quadruple, and so on the size of the net until no more Elo falls out of it?
To me, it seems an utter no-brainer.
If you examine the Elo of the LC0 nets, the larger the net, the larger the Elo. And it isn't close. The big nets CLOBBER the smaller ones.
I think that bigger and bigger nets should be constructed until it is no longer true.
Similarly with SF.
Yes, Albert spent a great deal of money testing out his ideas. But the resources he could purchase are not nearly so large as the free resource of the SF mega-team has at their very fingertips.
And yet this upstart beats them all:
http://www.cegt.net/40_40%20Rating%20Li ... liste.html
What did he do?
Well, one OBVIOUS thing is to double the net size.
Now, he also did special analysis to vary the input data, which is not to be discounted.
But why shouldn't the SF team double, quadruple, and so on the size of the net until no more Elo falls out of it?
To me, it seems an utter no-brainer.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
-
- Posts: 4889
- Joined: Thu Mar 09, 2006 6:34 am
- Location: Pen Argyl, Pennsylvania
Re: larger nets for SF?
hmmm... I see a difference in style of play and FRC was certainly better, but Elo gain from doubling? - from whatever possible gain was obtained, it does not appear to be worth the extra 20MB of space to store... just my $.02 .. I do like the fact that Albert tried something new and maybe he is on to something, but I am not sure yet.Dann Corbit wrote: ↑Sat Apr 17, 2021 8:47 am It appears that my point was missed entirely.
If you examine the Elo of the LC0 nets, the larger the net, the larger the Elo. And it isn't close. The big nets CLOBBER the smaller ones.
I think that bigger and bigger nets should be constructed until it is no longer true.
Similarly with SF.
Yes, Albert spent a great deal of money testing out his ideas. But the resources he could purchase are not nearly so large as the free resource of the SF mega-team has at their very fingertips.
And yet this upstart beats them all:
http://www.cegt.net/40_40%20Rating%20Li ... liste.html
What did he do?
Well, one OBVIOUS thing is to double the net size.
Now, he also did special analysis to vary the input data, which is not to be discounted.
But why shouldn't the SF team double, quadruple, and so on the size of the net until no more Elo falls out of it?
To me, it seems an utter no-brainer.
-
- Posts: 2662
- Joined: Wed Mar 10, 2010 10:18 pm
- Location: Hamburg, Germany
- Full name: Srdja Matovic
Re: larger nets for SF?
I think it is a trade-off, bigger nets = less nps = shallower AB searches. Elo gain by bigger nets vs. Elo gain by deeper searches, or alike. With more horse-power from vector units on CPU the net size will rise for sure.Dann Corbit wrote: ↑Sat Apr 17, 2021 8:47 am ...
But why shouldn't the SF team double, quadruple, and so on the size of the net until no more Elo falls out of it?
...
--
Srdja
-
- Posts: 1564
- Joined: Thu Jul 16, 2009 10:47 am
- Location: Almere, The Netherlands
Re: larger nets for SF?
It's nothing new, everybody understands that a larger network can hold more information. With current computers the storage space is not a problem too, it's all a trade-off between speed and network size. At the point that the Elo gain from increasing the network size becomes less than the Elo loss from the decreased speed you don't want to make it larger anymore.MikeB wrote: ↑Sat Apr 17, 2021 9:18 am hmmm... I see a difference in style of play and FRC was certainly better, but Elo gain from doubling? - from whatever possible gain was obtained, it does not appear to be worth the extra 20MB of space to store... just my $.02 .. I do like the fact that Albert tried something new and maybe he is on to something, but I am not sure yet.
-
- Posts: 476
- Joined: Sun Mar 17, 2019 12:00 pm
- Full name: Henk Drost
Re: larger nets for SF?
2 elo diff +-16 eloDann Corbit wrote: ↑Sat Apr 17, 2021 8:47 am It appears that my point was missed entirely.
If you examine the Elo of the LC0 nets, the larger the net, the larger the Elo. And it isn't close. The big nets CLOBBER the smaller ones.
I think that bigger and bigger nets should be constructed until it is no longer true.
Similarly with SF.
Yes, Albert spent a great deal of money testing out his ideas. But the resources he could purchase are not nearly so large as the free resource of the SF mega-team has at their very fingertips.
And yet this upstart beats them all:
http://www.cegt.net/40_40%20Rating%20Li ... liste.html
What did he do?
Well, one OBVIOUS thing is to double the net size.
Now, he also did special analysis to vary the input data, which is not to be discounted.
But why shouldn't the SF team double, quadruple, and so on the size of the net until no more Elo falls out of it?
To me, it seems an utter no-brainer.
FF2 net is verifiably weaker.
Bigger nets aren't new. They just haven't been proven to be stronger than the default arch yet.
-
- Posts: 4889
- Joined: Thu Mar 09, 2006 6:34 am
- Location: Pen Argyl, Pennsylvania
Re: larger nets for SF?
exactly, FF2 was double the size and how much Elo did we gain, it was disappointing ...Joost Buijs wrote: ↑Sat Apr 17, 2021 10:13 amIt's nothing new, everybody understands that a larger network can hold more information. With current computers the storage space is not a problem too, it's all a trade-off between speed and network size. At the point that the Elo gain from increasing the network size becomes less than the Elo loss from the decreased speed you don't want to make it larger anymore.MikeB wrote: ↑Sat Apr 17, 2021 9:18 am hmmm... I see a difference in style of play and FRC was certainly better, but Elo gain from doubling? - from whatever possible gain was obtained, it does not appear to be worth the extra 20MB of space to store... just my $.02 .. I do like the fact that Albert tried something new and maybe he is on to something, but I am not sure yet.
-
- Posts: 511
- Joined: Sun Apr 26, 2020 11:40 pm
- Full name: Brian D. Smith
Re: larger nets for SF?
But if "...Elo loss from the decreased speed"...would larger nets still be beneficial in certain areas? Maybe for long analysis or LTC (instead of simple engine vs engine quick play matchups)?MikeB wrote: ↑Sat Apr 17, 2021 3:31 pmexactly, FF2 was double the size and how much Elo did we gain, it was disappointing ...Joost Buijs wrote: ↑Sat Apr 17, 2021 10:13 amIt's nothing new, everybody understands that a larger network can hold more information. With current computers the storage space is not a problem too, it's all a trade-off between speed and network size. At the point that the Elo gain from increasing the network size becomes less than the Elo loss from the decreased speed you don't want to make it larger anymore.MikeB wrote: ↑Sat Apr 17, 2021 9:18 am hmmm... I see a difference in style of play and FRC was certainly better, but Elo gain from doubling? - from whatever possible gain was obtained, it does not appear to be worth the extra 20MB of space to store... just my $.02 .. I do like the fact that Albert tried something new and maybe he is on to something, but I am not sure yet.
-
- Posts: 1564
- Joined: Thu Jul 16, 2009 10:47 am
- Location: Almere, The Netherlands
Re: larger nets for SF?
Yes, I can imagine that for analysis without time constraints a larger net could be beneficial. It also depends upon the data used for training, if the information that the net can hold is larger than the information contained in the training data it will probably be counterproductive.Cornfed wrote: ↑Sat Apr 17, 2021 5:50 pmBut if "...Elo loss from the decreased speed"...would larger nets still be beneficial in certain areas? Maybe for long analysis or LTC (instead of simple engine vs engine quick play matchups)?MikeB wrote: ↑Sat Apr 17, 2021 3:31 pmexactly, FF2 was double the size and how much Elo did we gain, it was disappointing ...Joost Buijs wrote: ↑Sat Apr 17, 2021 10:13 amIt's nothing new, everybody understands that a larger network can hold more information. With current computers the storage space is not a problem too, it's all a trade-off between speed and network size. At the point that the Elo gain from increasing the network size becomes less than the Elo loss from the decreased speed you don't want to make it larger anymore.MikeB wrote: ↑Sat Apr 17, 2021 9:18 am hmmm... I see a difference in style of play and FRC was certainly better, but Elo gain from doubling? - from whatever possible gain was obtained, it does not appear to be worth the extra 20MB of space to store... just my $.02 .. I do like the fact that Albert tried something new and maybe he is on to something, but I am not sure yet.
-
- Posts: 12542
- Joined: Wed Mar 08, 2006 8:57 pm
- Location: Redmond, WA USA
Re: larger nets for SF?
There are a number of experiments conducted on the Rybka forum that show a direct relationship between net size and Elo increase.Raphexon wrote: ↑Sat Apr 17, 2021 10:28 am2 elo diff +-16 eloDann Corbit wrote: ↑Sat Apr 17, 2021 8:47 am It appears that my point was missed entirely.
If you examine the Elo of the LC0 nets, the larger the net, the larger the Elo. And it isn't close. The big nets CLOBBER the smaller ones.
I think that bigger and bigger nets should be constructed until it is no longer true.
Similarly with SF.
Yes, Albert spent a great deal of money testing out his ideas. But the resources he could purchase are not nearly so large as the free resource of the SF mega-team has at their very fingertips.
And yet this upstart beats them all:
http://www.cegt.net/40_40%20Rating%20Li ... liste.html
What did he do?
Well, one OBVIOUS thing is to double the net size.
Now, he also did special analysis to vary the input data, which is not to be discounted.
But why shouldn't the SF team double, quadruple, and so on the size of the net until no more Elo falls out of it?
To me, it seems an utter no-brainer.
FF2 net is verifiably weaker.
Bigger nets aren't new. They just haven't been proven to be stronger than the default arch yet.
Also, when it comes to solving tactical problems bigger nets are the clear winner.
I think we do not know what the best net size is. That is why I suggest trying lots of different sizes, including really large ones.
I guess that the hardware is important too. A cell phone is probably going to want a different net than a 256 core server,
and for LC0, a little card or running on CPU power will be different from two or three of the latest and greatest cards.
When you look at the Elo curves, they seem hardware limited and size limited. So, for instance, after a certain number of data points are fed into it, the strength appears to stop growing. So we have hit some kind of limit. Is the limit due to the size of the net? Is it due to the hardware capability? I guess that it is some of both.
Taking ideas is not a vice, it is a virtue. We have another word for this. It is called learning.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.
But sharing ideas is an even greater virtue. We have another word for this. It is called teaching.