Law of Large Numbers and Central Limit Theorem for Wide Two-layer Neural Networks: The Mini-Batch and Noisy Case

Score test - Wikipedia

Non-asymptotic approximations of Gaussian neural networks via...

There is a growing interest on large-width asymptotic and non-asymptotic properties of deep Gaussian neural networks (NNs), namely NNs with weights initialized as Gaussian distributions. For a...

Inference on the Change Point under a High Dimensional Covariance Shift

‘Alien Calculus’ Could Save Particle Physics From Infinities | Quanta Magazine

In the math of particle physics, every calculation should result in infinity. Physicists get around this by just ignoring certain parts of the equations — an approach that provides approximate answers. But by using the techniques known as “resurgence,” researchers hope to end the infinities and end up with perfectly precise predictions.