6 citations · 13 across the 4 of their papers we have counts for
Showing stat.MLShow all
2 papers · 1 filter
stat.ML2018
Approximate message-passing for convex optimization with non-separable penalties
Andre Manoel, Florent Krzakala, Gaël Varoquaux +2
We introduce an iterative optimization scheme for convex objectives consisting of a linear loss and a non-separable penalty, based on the expectation-consistent approximation and t…
stat.ML2017★ 6 cited
Streaming Bayesian inference: theoretical limits and mini-batch approximate message-passing
Andre Manoel, Florent Krzakala, Eric W. Tramel +1
In statistical learning for real-world large-scale data problems, one must often resort to "streaming" algorithms which operate sequentially on small batches of data. In this work,…