Time to rethink what Albert Silver has done?

[noobpwnftw]

it was a dead end

And it is dead.

Time to rethink? If it was just a translation into Dutch, it would've been stronger.

[Raphexon]

Yo, into wasps' nest, I am not into the details, but I read that Stockfish uses now Lc0 data for training, and doubled their net size. Time to rethink what Albert Silver has done? As far as I got it he used FatFritz 1 (Lc0 derivative) data for training and doubled the net size of the FatFritz 2 (Stockfish derivative) network.

--
Srdja

PS: not interested in discussing the marketing of ChessBase for FF2.

1. He used leela (FF1) data because he had

... the idea of converting it into NNUE usable data to train a network. He then rented 10 2080ti GPUs on Vast.ai for several months (at a cost of thousands of dollars) to generate the data needed to do this, since of course the FF1 data he had was completely insufficient as maybe only 300 thousand games were from the final net's full strength, the rest was much weaker, and therefore not of interest. Except to test the concept.

It just so happens that we independently discovered that lc0 data works well in our case.

A miracle!

2. Trying to increase the net size is a no brainer once the training and testing procedure is established and

... demonstrated by someone else first.

This was pretty much known from the beginning, as jjosh was training larger nets well before most people even knew about NNUE.

Quite true, and his result was some 50 Elo weaker. As a result, the popular belief was that it was a dead end as was repeatedly told anyone asking about larger net sizes in the SF Discord. Vondele's attempt to reproduce my result was also much weaker, but of course I was using higher quality data.

Still, as I mentioned elsewhere, I felt it would inspire others to try and of course improve my ideas and the proof is there. I'm genuinely glad.

How was Vondele's attempt "much weaker" when it produced nigh-identical results in H2H matches vs SFdev?

You also really can't stop lying, can you?

[AndrewGrant]

Yo, into wasps' nest, I am not into the details, but I read that Stockfish uses now Lc0 data for training, and doubled their net size. Time to rethink what Albert Silver has done? As far as I got it he used FatFritz 1 (Lc0 derivative) data for training and doubled the net size of the FatFritz 2 (Stockfish derivative) network.

--
Srdja

PS: not interested in discussing the marketing of ChessBase for FF2.

1. He used leela (FF1) data because he had

... the idea of converting it into NNUE usable data to train a network. He then rented 10 2080ti GPUs on Vast.ai for several months (at a cost of thousands of dollars) to generate the data needed to do this, since of course the FF1 data he had was completely insufficient as maybe only 300 thousand games were from the final net's full strength, the rest was much weaker, and therefore not of interest. Except to test the concept.

It just so happens that we independently discovered that lc0 data works well in our case.

A miracle!

2. Trying to increase the net size is a no brainer once the training and testing procedure is established and

... demonstrated by someone else first.

This was pretty much known from the beginning, as jjosh was training larger nets well before most people even knew about NNUE.

Quite true, and his result was some 50 Elo weaker. As a result, the popular belief was that it was a dead end as was repeatedly told anyone asking about larger net sizes in the SF Discord. Vondele's attempt to reproduce my result was also much weaker, but of course I was using higher quality data.

Still, as I mentioned elsewhere, I felt it would inspire others to try and of course improve my ideas and the proof is there. I'm genuinely glad.

Are you really acting like there was some big movement of people going "No! Its not possible! You could not possibly increase the size of the Network", and then you, the bold, brave, defiant Alberto showed the world what they refused to believe? Delusional.

[smatovic]

Alright guys, I see, this is about Ego, hence - personal thread Nazi moderation: we had our 5 minutes, let's lock the thread and move on.

--
Srdja

[hgm]

[Moderation] Locked at the request of the OP.