Search Results for author:
Found 3 papers, 0 papers with code
Label noise (stochastic) gradient descent implicitly solves the Lasso for quadratic parametrisation
Understanding the implicit bias of training algorithms is of crucial importance in order to explain the success of overparametrised neural networks.
Quasi-stationary distribution for the Langevin process in cylindrical domains, part I: existence, uniqueness and long-time convergence
Consider the Langevin process, described by a vector (position, momentum) in $\mathbb{R}^{d}\times\mathbb{R}^d$.
Probability Spectral Theory
Reweighting samples under covariate shift using a Wasserstein distance criterion
We study an optimal reweighting that minimizes the Wasserstein distance between the empirical measures of the two samples, and leads to an expression of the weights in terms of Nearest Neighbors.
