Speaker
Sophia Vent
(Institute for theoretical physics Heidelberg)
Description
We employ neural control variates to minimize the range of event weights and avoid negative weights for phase-space integration and event generation. A signed control variate, built from two normalizing flows, fulfills both tasks. Combined with neural importance sampling, it significantly reduces the computational cost of LO and NLO predictions. For the NLO case, our conditional neural control variate can be viewed as a trainable subtraction term, complementing the established physics subtraction schemes for enhanced sampling performance.
Authors
Ramon Winterhalder
(Università degli Studi di Milano)
Rebecca Revelli
(Heidelberg University)
Sophia Vent
(Institute for theoretical physics Heidelberg)
Theo Heimel
(UCLouvain)
Tilman Plehn