114 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Laboratoire d'Informatique de GrenobleFR18 papers
- Centre National de la Recherche ScientifiqueFR9 papers
- Criteo (France)FR6 papers
- Institut polytechnique de GrenobleFR6 papers
- Centre Inria de l'Université Grenoble AlpesFR5 papers
- Université Grenoble AlpesFR5 papers
- Institut national de recherche en sciences et technologies du numériqueFR4 papers
- École Polytechnique Fédérale de LausanneCH3 papers
- École Nationale Supérieure de l'Électronique et de ses ApplicationsFR2 papers
- École Normale Supérieure - PSLFR2 papers
- Equipes Traitement de l'Information et SystèmesFR2 papers
- Institut Polytechnique de BordeauxFR2 papers
5 papers · 1 filter
Regret minimization in stochastic non-convex learning via a proximal-gradient approach
Nadav Hallak, Panayotis Mertikopoulos, Volkan Cevher
Motivated by applications in machine learning and operations research, we study regret minimization with stochastic first-order oracle feedback in online constrained, and possibly…
The limits of min-max optimization algorithms: convergence to spurious non-critical sets
Ya-Ping Hsieh, Panayotis Mertikopoulos, Volkan Cevher
Compared to ordinary function minimization problems, min-max optimization algorithms encounter far greater challenges because of the existence of periodic cycles and similar phenom…
Fast Optimization with Zeroth-Order Feedback in Distributed, Multi-User MIMO Systems
Olivier Bilenne, Panayotis Mertikopoulos, E. Veronica Belmega
In this paper, we develop a gradient-free optimization methodology for efficient resource allocation in Gaussian MIMO multiple access channels. Our approach combines two main ingre…
A new regret analysis for Adam-type algorithms
Ahmet Alacaoglu, Yura Malitsky, Panayotis Mertikopoulos +1
In this paper, we focus on a theory-practice gap for Adam and its variants (AMSgrad, AdamNC, etc.). In practice, these algorithms are used with a constant first-order moment parame…
Explore Aggressively, Update Conservatively: Stochastic Extragradient Methods with Variable Stepsize Scaling
Yu-Guan Hsieh, Franck Iutzeler, Jérôme Malick +1
Owing to their stability and convergence speed, extragradient methods have become a staple for solving large-scale saddle-point problems in machine learning. The basic premise of t…