Quantum jamming: Critical properties of a quantum mechanical perceptron

In this Letter, we analyze the quantum dynamics of perceptron model: a particle is constrained on $N$-dimensional sphere, with $N\to \infty$, and subjected to set randomly placed hard-wall potentials. This model has several applications, ranging from learning protocols effective description an ensemble infinite-dimensional hard spheres in Euclidean space. We find that jamming transition shows critical exponents different classical case. also transition, unlike typical points, not confined zero-temperature axis, results are recovered only at $T=\infty$. Our findings have implications for theory glasses ultra-low temperatures study machine-learning algorithms.