5 citations · 6 across the 2 of their papers we have counts for
8 papers
Non-asymptotic approximations of neural networks by Gaussian processes
Ronen Eldan, Dan Mikulincer, Tselil Schramm
We study the extent to which wide neural networks may be approximated by Gaussian processes when initialized with random weights. It is a well-established fact that as the width of…
Stability estimates for invariant measures of diffusion processes, with applications to stability of moment measures and Stein kernels
Max Fathi, Dan Mikulincer
We investigate stability of invariant measures of diffusion processes with respect to distances on the coefficients, under an assumption of log-concavity. The method is a var…
Network size and weights size for memorization with two-layers neural networks
Sébastien Bubeck, Ronen Eldan, Yin Tat Lee +1
In 1988, Eric B. Baum showed that two-layers neural networks with threshold activation function can perfectly memorize the binary labels of points in general position in $\math…
A CLT in Stein's distance for generalized Wishart matrices and higher order tensors
Dan Mikulincer
We study the central limit theorem for sums of independent tensor powers, . We focus on the high-dimensional regime where $X_…
How to trap a gradient flow
Sébastien Bubeck, Dan Mikulincer
We consider the problem of finding an -approximate stationary point of a smooth function on a compact domain of . In contrast with dimension-free approac…
Stability of Talagrand's Gaussian transport-entropy inequality via the Föllmer process
Dan Mikulincer
We establish a dimension-free improvement of Talagrand's Gaussian transport-entropy inequality, under the assumption that the measures satisfy a Poincaré inequality. We also study…