“…Technically, we propose to use invertible networks (INNs) [11][12][13] to invert part of the LHC simulation chain. This application builds on a long list of one-directional applications of generative or similar networks to LHC simulations, including phase space integration [14,15], amplitudes [16,17], event generation [18][19][20][21][22], event subtraction [23], detector simulations [24][25][26][27][28][29][30][31][32], parton showers [33][34][35][36], or searches for physics beyond the Standard Model [37]. INNs are an alternative class of generative networks, based on normalizing flows [38][39][40][41].…”