Probing hidden spin order with interpretable machine learning
This work addresses the problem of discerning unconventional magnetic states for researchers in condensed matter physics, offering a tool to identify hidden orders and rule out spurious candidates, though it is incremental as it builds on existing machine learning approaches for spin systems.
The researchers tackled the challenge of identifying hidden spin orders, such as nematic states, in frustrated magnetic systems by developing a machine learning protocol that can detect these orders and extract their order parameters from seemingly featureless spin configurations. They demonstrated the method's capability by extracting analytical forms of nematic order parameter tensors up to rank 6.
The search of unconventional magnetic and nonmagnetic states is a major topic in the study of frustrated magnetism. Canonical examples of those states include various spin liquids and spin nematics. However, discerning their existence and the correct characterization is usually challenging. Here we introduce a machine-learning protocol that can identify general nematic order and their order parameter from seemingly featureless spin configurations, thus providing comprehensive insight on the presence or absence of hidden orders. We demonstrate the capabilities of our method by extracting the analytical form of nematic order parameter tensors up to rank 6. This may prove useful in the search for novel spin states and for ruling out spurious spin liquid candidates.