63.6k citations · 104.5k across the 42 of their papers we have counts for
Showing 2016Show all
3 papers · 1 filter
stat.ML2016★ 2 cited
On the convergence rate of the three operator splitting scheme
Fabian Pedregosa
The three operator splitting scheme was recently proposed by [Davis and Yin, 2015] as a method to optimize composite objective functions with one convex smooth term and two convex…
math.OC2016★ 10 cited
ASAGA: Asynchronous Parallel SAGA
Rémi Leblond, Fabian Pedregosa, Simon Lacoste-Julien
We describe ASAGA, an asynchronous parallel version of the incremental gradient algorithm SAGA that enjoys fast linear convergence rates. Through a novel perspective, we revisit an…
stat.ML2016★ 132 cited
Hyperparameter optimization with approximate gradient
Fabian Pedregosa
Most models in machine learning contain at least one hyperparameter to control for model complexity. Choosing an appropriate set of hyperparameters is both crucial in terms of mode…