Rigor with machine learning from field theory to the Poincar conjecture

Despite their successes, machine learning techniques are often stochastic, error-prone and blackbox. How could they then be used in fields such as theoretical physics and pure mathematics for which error-free results and deep understanding are a must? In this Perspective, we discuss techniques for obtaining zero-error results with machine learning, with a focus on theoretical physics and pure mathematics. Non-rigorous methods can enable rigorous results via conjecture generation or verification by reinforcement learning. We survey applications of these techniques-for-rigor ranging from string theory to the smooth 4D Poincare conjecture in low-dimensional topology. We also discuss connections between machine learning theory and mathematics or theoretical physics such as a new approach to field theory motivated by neural network theory, and a theory of Riemannian metric flows induced by neural network gradient descent, which encompasses Perelman's formulation of the Ricci flow that was used to solve the 3D Poincare conjecture. Machine learning techniques may appear ill-suited for application in fields that prioritize rigor and deep understanding; however, they have recently found unexpected uses in theoretical physics and pure mathematics. In this Perspective, Gukov, Halverson and Ruehle have discussed rigorous applications of machine learning to theoretical physics and pure mathematics.