Machine Learning of Thermodynamic Observables in the Presence of Mode Collapse
This work addresses a key computational challenge in physics for researchers in lattice field theories, but it is incremental as it reviews and discusses mitigation techniques for mode collapse rather than introducing a new method.
The paper tackles the problem of estimating free energy and other thermodynamic observables in lattice field theories by reviewing a deep generative model approach that directly estimates free energy at specific parameter points, contrasting with traditional Markov chain methods that require integration across parameter space.
Estimating the free energy, as well as other thermodynamic observables, is a key task in lattice field theories. Recently, it has been pointed out that deep generative models can be used in this context [1]. Crucially, these models allow for the direct estimation of the free energy at a given point in parameter space. This is in contrast to existing methods based on Markov chains which generically require integration through parameter space. In this contribution, we will review this novel machine-learning-based estimation method. We will in detail discuss the issue of mode collapse and outline mitigation techniques which are particularly suited for applications at finite temperature.