249 citations · 744 across the 13 of their papers we have counts for
Showing 2018Show all
3 papers · 1 filter
math.OC2018★ 249 cited
On Lazy Training in Differentiable Programming
Lenaic Chizat, Edouard Oyallon, Francis Bach
In a series of recent theoretical works, it was shown that strongly over-parameterized neural networks trained with gradient-based methods could converge exponentially fast to zero…
math.ST2018★ 127 cited
Sample Complexity of Sinkhorn divergences
Aude Genevay, Lénaic Chizat, Francis Bach +2
Optimal transport (OT) and maximum mean discrepancies (MMD) are now routinely used in machine learning to compare probability measures. We focus in this paper on \emph{Sinkhorn div…
math.OC2018★ 92 cited
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
Lenaic Chizat, Francis Bach
Many tasks in machine learning and signal processing can be solved by minimizing a convex function of a measure. This includes sparse spikes deconvolution or training a neural netw…