activity
20172026
most citedTight Nonparametric Convergence Rates for Stochastic Gradient Descent under the Noiseless Linear Model

16 citations · 32 across the 15 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

cs.LG2022★ 2 cited

Incremental Learning in Diagonal Linear Networks

Raphaël Berthier

Diagonal linear networks (DLNs) are a toy simplification of artificial neural networks; they consist in a quadratic reparametrization of linear regression inducing a sparse implici…

cs.DC2022★ 1 cited

Acceleration of Gossip Algorithms through the Euler-Poisson-Darboux Equation

Raphaël Berthier, Mufan Bill Li

Gossip algorithms and their accelerated versions have been studied exclusively in discrete time on graphs. In this work, we take a different approach, and consider the scaling limi…