Normalizing Flows for LHC Theory

Abstract Over the next years, measurements at LHC and HL-LHC will provide us with a wealth of new data. The best hope to answer fundamental questions, like nature dark matter, is adopt big data techniques in simulations analyses extract all relevant information. On theory side, physics crucially relies on our ability simulate events efficiently from first principles. These face unprecedented precision requirements match experimental accuracy. Innovative ML generative networks can help overcome limitations high dimensionality phase space. Such be employed within established simulation tools or as part framework. Since neural inverted, they open avenues analyses.