Publications
Chosen filters:
Chosen filters:
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems KU Leuven
BREGMAN FINITO/MISO FOR NONCONVEX REGULARIZED FINITE SUM MINIMIZATION WITHOUT LIPSCHITZ GRADIENT CONTINUITY KU Leuven University of Antwerp
Distributed Proximal Algorithms for Large-Scale Structured Optimization KU Leuven
Efficient first-order algorithms for large-scale distributed optimization is the main subject of investigation in this thesis. The algorithms considered cover a wide array of applications in machine learning, signal processing and control. In recent years, a large number of algorithms have been introduced that rely on (possibly a reformulation of) one of the classical splitting algorithms, specifically forward-backward, Douglas-Rachford and ...
A New Randomized Block-Coordinate Primal-Dual Proximal Algorithm for Distributed Optimization KU Leuven
This paper proposes TriPD, a new primal-dual algorithm for minimizing the sum of a Lipschitz-differentiable convex function and two possibly nonsmooth convex functions, one of which is composed with a linear mapping. We devise a randomized block-coordinate version of the algorithm which converges under the same stepsize conditions as the full algorithm. It is shown that both the original as well as the block-coordinate scheme feature linear ...
Multi-agent structured optimization over message-passing architectures with bounded communication delays KU Leuven
© 2018 IEEE. We consider the problem of solving structured convex optimization problems over a network of agents with communication delays. It is assumed that each agent performs its local updates using possibly outdated information from its neighbors under the assumption that the delay with respect to each neighbor is bounded but otherwise arbitrary. The private objective of each agent is represented by the sum of two possibly nonsmooth ...
Primal-dual proximal algorithms for structured convex optimization : a unifying framework KU Leuven
© 2018, Springer Nature Switzerland AG. We present a simple primal-dual framework for solving structured convex optimization problems involving the sum of a Lipschitz-differentiable function and two nonsmooth proximable functions, one of which is composed with a linear mapping. The framework is based on the recently proposed asymmetric forward-backward-adjoint three-term splitting (AFBA); depending on the value of two parameters, (extensions of) ...
Plug and Play Distributed Model Predictive Control with Dynamic Coupling: A Randomized Primal-dual Proximal Algorithm KU Leuven
© 2018 European Control Association (EUCA). This paper proposes an algorithm for distributed model predictive control that is based on a primal-dual proximal algorithm developed recently by two of the authors. The proposed scheme does not require strong convexity, involves one round of communication at every iteration and is fully distributed. In fact, both the iterations and the stepsizes are computed using only local information. This allows a ...