Recent works on neural contextual bandits have achieved compelling performances due to
their ability to leverage the strong representation power of neural networks (NNs) for reward …

We address multi-agent best arm identification with privacy guarantees. In this setting,
agents collaborate by communicating to find the optimal arm. To avoid leaking sensitive data …

Federated learning (FL) in its classic form involves the collaborative training of supervised
learning models (eg, neural networks) among multiple agents/clients. However, in addition …

The trade-off between exploration and exploitation has been one of the main challenges for
ensuring sampling efficiency, optimal solution, and transferability of reinforcement learning …

Federated learning (FL), also referred to as collaborative learning, uses a number of
dispersed edge devices or servers to run the training algorithms, without exchanging local …

The federated learning paradigm allows several data owners to contribute to a machine
learning task without exposing their potentially sensitive data. We focus on cumulative …

A cryptographic protocol establishes a series of interactions among users to deliver a given
functionality while ensuring various properties, a protocol being considered secure when it …

Nowadays there are more and more items available online, this makes it hard for users to
find items that they like. Recommender systems aim to find the item who best suits the user …

L'axe Système d'Information et de Communication (SIC) du Laboratoire d'Informatique, de
Modélisation et d'Optimisation des Systèmes (LIMOS) regroupe les travaux en interaction …