Machine learning tools are commonly used in modern high energy physics (HEP) experiments. Different models, such as boosted decision trees (BDT) and artificial neural networks (ANN), are widely used in analyses and even in the software triggers.
In most cases, these are classification models used to select the "signal" events from data. Monte Carlo simulated events typically take part in training of these models. While the results of the simulation are expected to be close to real data, in practical cases there is notable disagreement between simulated and observed data. In order to use available simulation in training, corrections must be introduced to generated data. One common approach is reweighting - assigning weights to the simulated events. We present a novel method of event reweighting based on boosted decision trees. The problem of checking the quality of reweighting step in analyses is also discussed.
[1]
D Martschei,et al.
Advanced event reweighting using multivariate analysis
,
2012
.
[2]
Francesco Dettori,et al.
Flavours of Physics: the machine learning challenge for the search of τ−→ μ−μ−μ+ decays at LHCb
,
2015
.
[3]
Yoshua Bengio,et al.
Generative Adversarial Nets
,
2014,
NIPS.
[4]
René F. Kizilcec,et al.
Reducing non-response bias with survey reweighting: applications for online learning researchers
,
2014,
L@S.
[5]
Takafumi Kanamori,et al.
Density Ratio Estimation in Machine Learning
,
2012
.
[6]
J. Friedman.
On Multivariate Goodness-of-Fit and Two-Sample Testing
,
2004
.
[7]
Alex Rogozhnikov,et al.
LHCb Topological Trigger Reoptimization
,
2015,
1510.00572.
[8]
Yoav Freund,et al.
Experiments with a New Boosting Algorithm
,
1996,
ICML.