Comments (6)
@acampove do you maybe have sources for
(from studies done by other people)
I would, AFAIU, second the argument of @arogozhnikov that, in general, you can do that
Hi Jonas,
This is what I remember Christoph Langenbruch said once in a meeting the measurement of the Bs-> phi mumu branching ratio. I would check their note or just talk to him, maybe you know him better than I do :)
Cheers.
from hep_ml.
Estimating correlation is a dead thing for that many numbers.
Better just model that correlation with training multiple models (e.g. by different cross-val splits), and estimate error of downstream processing by having multiple replicas
val1 = f(x_i, w_1i)
val2 = f(x_i, w_2i)
val2 = f(x_i, w_3i)
etc.
from hep_ml.
That approach would mean doing probably 200 trainings for the MVA. The real data usually is background subtracted using the sPlot technique. Apparently (from studies done by other people) we cannot bootstrap the sweighted sample, we have to:
- Bootstrap the unweighted data + simulation
- Obtain the sweights doing the fit.
- Train the MVA on the bootstrapped data and simulation
Many times, which seems very challenging computationally. In case of 2D or even 3D reweighting, I think this just means that we should not use hep_ml, given that obtaining uncertainties is highly non trivial and a number without uncertainties is pretty useless. Hep_ml would only be an alternative once you start thinking of reweighting in higher dimensions.
from hep_ml.
By the way, the bootstrapping argument also applies to k-Folding.
from hep_ml.
You surely can subsample sweighted samples. Opposite would mean your fitting is unstable (and hence probably wrong).
from hep_ml.
@acampove do you maybe have sources for
(from studies done by other people)
I would, AFAIU, second the argument of @arogozhnikov that, in general, you can do that
from hep_ml.
Related Issues (20)
- Random behavior of GBReweighter and UGradientBoostingClassifier
- Nominal weights when correcting already weighted original HOT 1
- Assertion Error with UGradientBoost HOT 1
- sPlot returns NAN sWeights HOT 3
- Odd behaviour of GBReweighter HOT 3
- Using sWeights with GBReweighter HOT 1
- Saving uboost BDT with tf/keras base estimators HOT 5
- Persistify GBReweighter instance HOT 1
- Create a new release? HOT 1
- Theano is going away HOT 1
- Benchmark with independent classification model HOT 3
- New release? HOT 2
- Large variations in signal/background distributions HOT 7
- GBReweighter KeyError: 'squared_error' ?? HOT 7
- Porting loss function to XGBoost HOT 1
- numpy.float and numpy.int deprecated/removed in newer versions of numpy HOT 3
- GPU Acceleration in GBDT HOT 6
- Documenting behavior of normalization HOT 1
- GBReweights seems to be not working in my case HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hep_ml.