Fixed-Budget Real-Valued Combinatorial Pure Exploration of Multi-Armed Bandit
S Nakamura, M Sugiyama - International Conference on …, 2024 - proceedings.mlr.press
We study the real-valued combinatorial pure exploration of the multi-armed bandit in the
fixed-budget setting. We first introduce an algorithm named the Combinatorial Successive …
fixed-budget setting. We first introduce an algorithm named the Combinatorial Successive …
Truthful Bandit Mechanisms for Repeated Two-stage Ad Auctions
Online advertising platforms leverage a two-stage auction architecture to deliver
personalized ads to users with low latency. The first stage efficiently selects a small subset of …
personalized ads to users with low latency. The first stage efficiently selects a small subset of …
Distributed robust bandits with efficient communication
A Wang, Z Qin, L Zheng, D Li… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The Distributed Multi-Armed Bandit (DMAB) is a powerful framework for studying many
network problems. The DMAB is typically studied in a paradigm, where signals activate each …
network problems. The DMAB is typically studied in a paradigm, where signals activate each …
[PDF][PDF] Robust Matroid Bandit Optimization against Adversarial Contamination
In this paper, we consider the matroid bandit optimization problem, a fundamental and
widely applicable framework for combinatorial multi-armed bandits where the action space …
widely applicable framework for combinatorial multi-armed bandits where the action space …