Connecting Dualities and Machine Learning
This work connects machine learning to theoretical physics by enabling automated discovery of dualities, which is incremental but novel in its interdisciplinary approach.
The paper tackled the problem of discovering dual data representations in supervised classification by enforcing them in neural network latent dimensions, resulting in the first proof-of-concept that computers can find dualities, as demonstrated with discrete Fourier transformation and Ising models.
Dualities are widely used in quantum field theories and string theory to obtain correlation functions at high accuracy. Here we present examples where dual data representations are useful in supervised classification, linking machine learning and typical tasks in theoretical physics. We then discuss how such beneficial representations can be enforced in the latent dimension of neural networks. We find that additional contributions to the loss based on feature separation, feature matching with respect to desired representations, and a good performance on a `simple' correlation function can lead to known and unknown dual representations. This is the first proof of concept that computers can find dualities. We discuss how our examples, based on discrete Fourier transformation and Ising models, connect to other dualities in theoretical physics, for instance Seiberg duality.