Comparing traditional and deep-learning techniques of kinematic reconstruction for polarization discrimination in vector boson scattering
M. Grossi, J. Novak, B. Kerševan, D. Rebuzzi
Abstract
Abstract Measuring longitudinally polarized vector boson scattering in $$\mathrm {WW}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>WW</mml:mi> </mml:math> channel is a promising way to investigate unitarity restoration with the Higgs mechanism and to search for possible physics beyond the Standard Model. In order to perform such a measurement, it is crucial to develop an efficient reconstruction of the full $$\mathrm {W}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>W</mml:mi> </mml:math> boson kinematics in leptonic decays with the focus on polarization measurements. We investigated several approaches, from traditional ones up to advanced deep neural network structures, and we compared their abilities in reconstructing the $$\mathrm {W}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>W</mml:mi> </mml:math> boson reference frame and in consequently measuring the longitudinal fraction $$\mathrm {W}_{\text {L}}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:msub> <mml:mi>W</mml:mi> <mml:mtext>L</mml:mtext> </mml:msub> </mml:math> in both semi-leptonic and fully-leptonic $$\mathrm {WW}$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mi>WW</mml:mi> </mml:math> decay channels.