2 papers
cs.LG2026
Offline Local Search for Online Stochastic Bandits
Gerdus Benadè, Rathish Das, Thomas Lavastida
Combinatorial multi-armed bandits provide a fundamental online decision-making environment where a decision-maker interacts with an environment across time steps, each time sel…
cs.LG2024
Binary Search with Distributional Predictions
Michael Dinitz, Sungjin Im, Thomas Lavastida +3
Algorithms with (machine-learned) predictions is a powerful framework for combining traditional worst-case algorithms with modern machine learning. However, the vast majority of wo…