Re: Question on Texel's Tuning Method
Posted: Fri Jul 10, 2020 4:03 pm
It isn't only to get the probabilities but the absolute values will have a different impact on the error:
Code: Select all
0.61 (80cp) 0.54 (30cp) 0.07 (error)
0.97 (580cp) 0.95 (530cp) 0.02 (error)
What you're saying makes sense. However, the results you showed aren't what I would expect from texel tuning, at least from the algo listed on CPW. Instead, I would expect to see:Desperado wrote: ↑Fri Jul 10, 2020 5:03 pmIt isn't only to get the probabilities but the absolute values will have a different impact on the error:
The error value of 50 cp for the sigmoid function is smaller for large scores than for smaller scores.For this reason the tuning considers 80/30 cp errors for "unclear" positions to be removed first than for decisive positions such as 580/530 cp values.Code: Select all
0.61 (80cp) 0.54 (30cp) 0.07 (error) 0.97 (580cp) 0.95 (530cp) 0.02 (error)
This can be explicitly done by using weights if the tuner uses absolute errors.(i guess...)
Code: Select all
1.00, 0.54 (30cp) 0.46 (error)
1.00, 0.95 (530cp) 0.05 (error)
Ok, using result values (fixed bounds), we cannot generate errors that have the same amount in relation to the absolute score.odomobo wrote: ↑Fri Jul 10, 2020 5:45 pmWhat you're saying makes sense. However, the results you showed aren't what I would expect from texel tuning, at least from the algo listed on CPW. Instead, I would expect to see:Desperado wrote: ↑Fri Jul 10, 2020 5:03 pmIt isn't only to get the probabilities but the absolute values will have a different impact on the error:
The error value of 50 cp for the sigmoid function is smaller for large scores than for smaller scores.For this reason the tuning considers 80/30 cp errors for "unclear" positions to be removed first than for decisive positions such as 580/530 cp values.Code: Select all
0.61 (80cp) 0.54 (30cp) 0.07 (error) 0.97 (580cp) 0.95 (530cp) 0.02 (error)
This can be explicitly done by using weights if the tuner uses absolute errors.(i guess...)
Code: Select all
1.00, 0.54 (30cp) 0.46 (error) 1.00, 0.95 (530cp) 0.05 (error)
Code: Select all
general result values are: 1.0 / 0.5 / 0.0
score: +30 cp -> 0.54
1. error to result 0.0: 0.54
2. error to result 1.0: 0.46
3. error to result 0.5: 0.04
score: +530 cp -> 0.95
4. error to result 0.0: 0.95
5. error to result 1.0: 0.05
6. error to result 0.5: 0.45
Code: Select all
example:
2b1r1k1/1pq1bpp1/p1n4p/3n4/2P1p3/1N2B2P/PP2QPP1/3R1BK1 w - - ce -33 acd 3 bm cxd5