1 citations · 1 across the 3 of their papers we have counts for
4 papers
DAOCP: a dual active set solver for optimal control problems
Alberto Zaupa, Samuel Erickson, Mikael Johansson
We present DAOCP, a dual active set solver for linear quadratic optimal control problems with stage-wise equality and inequality constraints. Active set methods are leading Model P…
Clipping Makes Distributed and Federated Asynchronous SGD Robust to Stragglers
Samuel Erickson, Mikael Johansson
In modern machine learning, parallelization of training is an important strategy for increasing scale. Asynchronous stochastic gradient descent (ASGD), which maximizes the utilizat…
Data-Driven Laplacian-Constrained Personalized Federated Learning
Samuel Erickson, Mikael Johansson
Personalization addresses one of the defining challenges in federated learning: statistical heterogeneity among clients. We show that the dissimilarity between the ideal personaliz…
Non-asymptotic Estimation of Sparse Partial Correlation via Joint Partial Regression
Samuel Erickson, Tobias Rydén
Partial correlation analysis is widely used in modern multivariate analysis. However, prior methods lack non-asymptotic guarantees and have slow asymptotic estimation rates. We pre…