For bilinear g(c; β) = c^T A β in compact convex minimax problems, ADMM reduces to alternating a generalized projection onto S and Euclidean projection onto C.
Distributed optimization and statistical learning via the alternating direction method of multipliers
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
fields
math.OC 2years
2026 2verdicts
UNVERDICTED 2roles
method 1polarities
use method 1representative citing papers
A sketched Nesterov projected gradient solver with GPU acceleration solves large mean-variance portfolio optimization problems orders of magnitude faster than standard solvers while providing approximation guarantees.
citing papers explorer
-
Solving Minimax Problems with Bilinear Objectives with ADMM
For bilinear g(c; β) = c^T A β in compact convex minimax problems, ADMM reduces to alternating a generalized projection onto S and Euclidean projection onto C.
-
Scalable Mean-Variance Portfolio Optimization via Subspace Embeddings and GPU-Friendly Nesterov-Accelerated Projected Gradient
A sketched Nesterov projected gradient solver with GPU acceleration solves large mean-variance portfolio optimization problems orders of magnitude faster than standard solvers while providing approximation guarantees.