Characterizing 4-string contact interaction using machine learning
This work addresses a specific challenge in theoretical physics by applying machine learning to string theory, representing an incremental advancement in computational methods for this domain.
The authors tackled the problem of characterizing the geometry of 4-string contact interactions in closed string field theory by using machine learning to obtain Strebel quadratic differentials and compute mapping radii, achieving good agreement with existing literature in computing the 4-tachyon contact term.
The geometry of 4-string contact interaction of closed string field theory is characterized using machine learning. We obtain Strebel quadratic differentials on 4-punctured spheres as a neural network by performing unsupervised learning with a custom-built loss function. This allows us to solve for local coordinates and compute their associated mapping radii numerically. We also train a neural network distinguishing vertex from Feynman region. As a check, 4-tachyon contact term in the tachyon potential is computed and a good agreement with the results in the literature is observed. We argue that our algorithm is manifestly independent of number of punctures and scaling it to characterize the geometry of $n$-string contact interaction is feasible.