Concept
Équilibre corrélé
Publications associées (27)
Computational Homogenization for Inverse Design of Surface-based Inflatables
Mark Pauly, Florin Isvoranu, Francis Julian Panetta, Uday Kusupati, Seiichi Eduardo Suzuki Erazo, Yingying Ren
Surface-based inflatables are composed of two thin layers of nearly inextensible sheet material joined together along carefully selected fusing curves. During inflation, pressure forces separate the two sheets to maximize the enclosed volume. The fusing c ...
2024Identifying invariant solutions of wall-bounded three-dimensional shear flows using robust adjoint-based variational techniques
Tobias Schneider, Omid Ashtari
Invariant solutions of the Navier-Stokes equations play an important role in the spatiotemporally chaotic dynamics of turbulent shear flows. Despite the significance of these solutions, their identification remains a computational challenge, rendering many ...
Cambridge2023Scalable Multi-agent Coordination and Resource Sharing
A plethora of real world problems consist of a number of agents that interact, learn, cooperate, coordinate, and compete with others in ever more complex environments. Examples include autonomous vehicles, robotic agents, intelligent infrastructure, IoT de ...
EPFL2022Decoding of error-related potentials in continuous feedback protocols for personalized human computer interaction
The ability to notice erroneous behavior is crucial for effective training. Within the framework of neuroprosthetics, numerous studies in electroencephalography (EEG) confirm the existence of neural correlates when humans perceive the erroneous actions of ...
EPFL2021Convergence without Convexity: Sampling, Optimization, and Games
Many important problems in contemporary machine learning involve solving highly non- convex problems in sampling, optimization, or games. The absence of convexity poses significant challenges to convergence analysis of most training algorithms, and in some ...
EPFL2020Out-of-equilibrium phase diagram of long-range superconductors
Within the ultimate goal of classifying universality in quantum many-body dynamics, understanding the relation between out-of-equilibrium and equilibrium criticality is a crucial objective. Models with power-law interactions exhibit rich well-understood cr ...
2020No-Regret Learning in Unknown Games with Correlated Payoffs
Maryam Kamgarpour, Andreas Krause, Ilija Bogunovic
We consider the problem of learning to play a repeated multi-agent game with an unknown reward function. Single player online learning algorithms attain strong regret bounds when provided with full information feedback, which unfortunately is unavailable i ...
Curran Associates, Inc.2019