"Application of machine learning techniques to the estimation of thermodynamic observables" (Paolo Stornati, DESY Zeuthen) Abstract: In this seminar I will discuss the application of deep generative machine learning models to lattice field theory. More specifically, I will show that these models can be used to estimate the absolute value of the free energy. The state of the art method for computing thermodynamic observables is Markov Chain Monte Carlo (MCMC). MCMC based methods are limited only to the estimation of free energy differences, which is very difficult in certain cases. I will compare the two methods by studying the 2-dimensional $\phi^4$ theory in numerical experiments.