Stockfish classical going downhill now

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Dann Corbit, Harvey Williamson

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.
Post Reply
Jouni
Posts: 2388
Joined: Wed Mar 08, 2006 7:15 pm

Stockfish classical going downhill now

Post by Jouni » Mon Dec 21, 2020 5:07 pm

Current SF classical vs latest version before NNUE:

ELO: -19.66 +-4.3 (95%) LOS: 0.0%
Total: 6440 W: 771 L: 1135 D: 4534
Ptnml(0-2): 84, 760, 1833, 522, 21

I am not surprised at all!
Jouni

Dicaste
Posts: 108
Joined: Mon Apr 16, 2012 5:23 pm
Location: Istanbul, TURKEY

Re: Stockfish classical going downhill now

Post by Dicaste » Mon Dec 21, 2020 5:20 pm

They should separate the development of classical stockfish like komodo did i think. NNUE is much more superior to classical stockfish i only tried once and i instantly hate it.

Madeleine Birchfield
Posts: 296
Joined: Tue Sep 29, 2020 2:29 pm
Location: Dublin, Ireland
Full name: Madeleine Birchfield

Re: Stockfish classical going downhill now

Post by Madeleine Birchfield » Mon Dec 21, 2020 8:26 pm

Dicaste wrote:
Mon Dec 21, 2020 5:20 pm
They should separate the development of classical stockfish like komodo did i think. NNUE is much more superior to classical stockfish i only tried once and i instantly hate it.
AFAIK, the classical evaluation is still used when UseNNUE is set to true. Above a certain evaluation threshold, the classical evaluation is used instead of NNUE because it is faster to calculate than NNUE evaluation and there isn't much difference between the two when the evaluation is about +5 or +10.

Dicaste
Posts: 108
Joined: Mon Apr 16, 2012 5:23 pm
Location: Istanbul, TURKEY

Re: Stockfish classical going downhill now

Post by Dicaste » Mon Dec 21, 2020 9:48 pm

Faster calculation doesn't mean everything.

Pi4Chess
Posts: 237
Joined: Mon Nov 16, 2020 11:13 am
Full name: Manuel Rivera

Re: Stockfish classical going downhill now

Post by Pi4Chess » Tue Dec 22, 2020 11:46 am

Of course classical modifications are only tested now in situations where NNUE is not used (in default hybrid mode). So it will only become stronger where NNUE is less stronger than classical.

Jouni
Posts: 2388
Joined: Wed Mar 08, 2006 7:15 pm

Re: Stockfish classical going downhill now

Post by Jouni » Tue Dec 22, 2020 1:53 pm

But what's this test now measuring?

https://tests.stockfishchess.org/tests/ ... 9192d3958b

I don't get it. Classical vs "classical", what !?!?
Jouni

Alayan
Posts: 527
Joined: Tue Nov 19, 2019 7:48 pm
Full name: Alayan Feh

Re: Stockfish classical going downhill now

Post by Alayan » Tue Dec 22, 2020 2:26 pm

Pi4Chess wrote:
Tue Dec 22, 2020 11:46 am
Of course classical modifications are only tested now in situations where NNUE is not used (in default hybrid mode). So it will only become stronger where NNUE is less stronger than classical.
This is wrong. Classical eval patches are tested with NNUE off.

Pi4Chess
Posts: 237
Joined: Mon Nov 16, 2020 11:13 am
Full name: Manuel Rivera

Re: Stockfish classical going downhill now

Post by Pi4Chess » Tue Dec 22, 2020 3:11 pm

Alayan wrote:
Tue Dec 22, 2020 2:26 pm
Pi4Chess wrote:
Tue Dec 22, 2020 11:46 am
Of course classical modifications are only tested now in situations where NNUE is not used (in default hybrid mode). So it will only become stronger where NNUE is less stronger than classical.
This is wrong. Classical eval patches are tested with NNUE off.
Ok then I don't understand why classical elo is going down as stated by OP.

jhellis3
Posts: 488
Joined: Fri Aug 16, 2013 10:36 pm

Re: Stockfish classical going downhill now

Post by jhellis3 » Tue Dec 22, 2020 5:09 pm

What is happening is the superior NNUE eval allows for more aggressive search optimizations (narrower search) than what was/is optimal with only hand-coded eval.

Using classical eval still has the more aggressive pruning, which is not optimal for it.

Pi4Chess
Posts: 237
Joined: Mon Nov 16, 2020 11:13 am
Full name: Manuel Rivera

Re: Stockfish classical going downhill now

Post by Pi4Chess » Tue Dec 22, 2020 7:09 pm

jhellis3 wrote:
Tue Dec 22, 2020 5:09 pm
What is happening is the superior NNUE eval allows for more aggressive search optimizations (narrower search) than what was/is optimal with only hand-coded eval.

Using classical eval still has the more aggressive pruning, which is not optimal for it.
Thanks for the explanation.

Post Reply