Add to ORKGInternational audienceWe introduce and analyze a new family of first-order optimization algorithms which generalizes and unifies both mirror descent and dual averaging. Within the framework of this family, we define new algorithms for constrained optimization that combines the advantages of mirror descent and dual averaging. Our preliminary simulation study shows that these new algorithms significantly outperform available methods in some situations. 21 References 21 Appendix A. Convex analysis tools 24 Appendix B. Postponed proofs 2
Averaging scheme has attracted extensive attention in deep learning as well as traditional machine l...
International audienceDeterministic and stochastic first order algorithms of large-scale convex opti...
305 pagesThis thesis concerns the foundations of first-order optimization theory. In recent years, t...
International audienceWe introduce and analyze a new family of first-order optimization algorithms w...
arXiv - Mathematiques - Optimization and ControlWe introduce and analyse a new family of algorithms ...
We present a new method for regularized convex optimization and analyze it under both online and sto...
First-order methods play a central role in large-scale convex optimization. Even though many variati...
International audienceGiven a convex optimization problem and its dual, there are many possible firs...
First-order methods play a central role in large-scale convex optimization. Despite their various fo...
Thesis (Ph.D.)--University of Washington, 2017Convex optimization is more popular than ever, with ex...
This monograph presents the main mathematical ideas in convex opti-mization. Starting from the funda...
Abstract Recently, distributed convex optimization using a multiagent system has received much atten...
Free to read at publisher website We study accelerated descent dynamics for constrained convex optim...
A dual subgradient method is proposed for solving convex optimization problems with linear constrain...
First-order methods are gaining substantial interest in the past two decades because of their superi...
Averaging scheme has attracted extensive attention in deep learning as well as traditional machine l...
International audienceDeterministic and stochastic first order algorithms of large-scale convex opti...
305 pagesThis thesis concerns the foundations of first-order optimization theory. In recent years, t...
International audienceWe introduce and analyze a new family of first-order optimization algorithms w...
arXiv - Mathematiques - Optimization and ControlWe introduce and analyse a new family of algorithms ...
We present a new method for regularized convex optimization and analyze it under both online and sto...
First-order methods play a central role in large-scale convex optimization. Even though many variati...
International audienceGiven a convex optimization problem and its dual, there are many possible firs...
First-order methods play a central role in large-scale convex optimization. Despite their various fo...
Thesis (Ph.D.)--University of Washington, 2017Convex optimization is more popular than ever, with ex...
This monograph presents the main mathematical ideas in convex opti-mization. Starting from the funda...
Abstract Recently, distributed convex optimization using a multiagent system has received much atten...
Free to read at publisher website We study accelerated descent dynamics for constrained convex optim...
A dual subgradient method is proposed for solving convex optimization problems with linear constrain...
First-order methods are gaining substantial interest in the past two decades because of their superi...
Averaging scheme has attracted extensive attention in deep learning as well as traditional machine l...
International audienceDeterministic and stochastic first order algorithms of large-scale convex opti...
305 pagesThis thesis concerns the foundations of first-order optimization theory. In recent years, t...