[HTML][HTML] Optimization algorithms as robust feedback controllers
Mathematical optimization is one of the cornerstones of modern engineering research and
practice. Yet, throughout all application domains, mathematical optimization is, for the most …
practice. Yet, throughout all application domains, mathematical optimization is, for the most …
On gradient descent ascent for nonconvex-concave minimax problems
We consider nonconvex-concave minimax problems, $\min_ {\mathbf {x}}\max_ {\mathbf
{y}\in\mathcal {Y}} f (\mathbf {x},\mathbf {y}) $, where $ f $ is nonconvex in $\mathbf {x} $ but …
{y}\in\mathcal {Y}} f (\mathbf {x},\mathbf {y}) $, where $ f $ is nonconvex in $\mathbf {x} $ but …
What is local optimality in nonconvex-nonconcave minimax optimization?
Minimax optimization has found extensive applications in modern machine learning, in
settings such as generative adversarial networks (GANs), adversarial training and multi …
settings such as generative adversarial networks (GANs), adversarial training and multi …
The limit points of (optimistic) gradient descent in min-max optimization
C Daskalakis, I Panageas - Advances in neural information …, 2018 - proceedings.neurips.cc
Motivated by applications in Optimization, Game Theory, and the training of Generative
Adversarial Networks, the convergence properties of first order methods in min-max …
Adversarial Networks, the convergence properties of first order methods in min-max …
Tutorial on dynamic average consensus: The problem, its applications, and the algorithms
Technological advances in ad hoc networking and the availability of low-cost reliable
computing, data storage, and sensing devices have made scenarios possible where the …
computing, data storage, and sensing devices have made scenarios possible where the …
Electrical networks and algebraic graph theory: Models, properties, and applications
F Dörfler, JW Simpson-Porco… - Proceedings of the IEEE, 2018 - ieeexplore.ieee.org
Algebraic graph theory is a cornerstone in the study of electrical networks ranging from
miniature integrated circuits to continental-scale power systems. Conversely, many …
miniature integrated circuits to continental-scale power systems. Conversely, many …
Interaction matters: A note on non-asymptotic local convergence of generative adversarial networks
Motivated by the pursuit of a systematic computational and algorithmic understanding of
Generative Adversarial Networks (GANs), we present a simple yet unified non-asymptotic …
Generative Adversarial Networks (GANs), we present a simple yet unified non-asymptotic …
Policy optimization provably converges to Nash equilibria in zero-sum linear quadratic games
We study the global convergence of policy optimization for finding the Nash equilibria (NE)
in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of …
in zero-sum linear quadratic (LQ) games. To this end, we first investigate the landscape of …
On the exponential stability of primal-dual gradient dynamics
Continuous time primal-dual gradient dynamics (PDGD) that find a saddle point of a
Lagrangian of an optimization problem have been widely used in systems and control. While …
Lagrangian of an optimization problem have been widely used in systems and control. While …
Local saddle point optimization: A curvature exploitation approach
Gradient-based optimization methods are the most popular choice for finding local optima
for classical minimization and saddle point problems. Here, we highlight a systemic issue of …
for classical minimization and saddle point problems. Here, we highlight a systemic issue of …