On regret with multiple best arms

Y Zhu, R Nowak - Advances in Neural Information …, 2020 - proceedings.neurips.cc
We study a regret minimization problem with the existence of multiple best/near-optimal
arms in the multi-armed bandit setting. We consider the case when the number of …

A distributed algorithm for multi-armed bandit with homogeneous rewards over directed graphs

J Zhu, J Liu - 2021 American Control Conference (ACC), 2021 - ieeexplore.ieee.org
This paper studies a distributed multi-armed bandit problem over a network of N agents
whose neighbor relationships are described by a directed graph G. Each agent makes a …

A law of robustness beyond isoperimetry

Y Wu, H Huang, H Zhang - International Conference on …, 2023 - proceedings.mlr.press
We study the robust interpolation problem of arbitrary data distributions supported on a
bounded space and propose a two-fold law of robustness. Robust interpolation refers to the …

Faster Homomorphic DFT and Speech Analysis for Torus Fully Homomorphic Encryption

KH Lee, YB Jeon, JW Yoon - 2024 IEEE 9th European …, 2024 - ieeexplore.ieee.org
Recent speech-based services such as voice assistants and cloud computing services have
brought security concerns, since those services constantly send user's speech data to the …

[PDF][PDF] Apprentissage par transfert dans les réseaux profonds: Application à la classification d'images

PJ Nour-Eddine, PC Ghizlane, FST Fès, PE Mohamed… - memoirepfe.fst-usmba.ac.ma
L'un des problèmes les plus courants auxquels sont confrontés les professionnels de la
science des données est d'éviter le sur-apprentissage, c'est la situation où notre modèle …