analiza aiqbench
This research introduces Latent Order Bandits (LOB), a novel algorithmic framework that relaxes strict assumptions in sequential decision-making by leveraging partial order constraints on action preferences rather than full reward distributions. By enabling models where instances within the same latent state share preference rankings but vary in scale, this approach significantly improves sample efficiency for personalization tasks like streaming recommendations without requiring accurate posterior knowledge of all reward parameters. The study provides theoretical regret bounds and empirical evidence that LOB outperforms existing methods when dealing with heterogeneous user scaling behaviors across shared contexts.
Latent Order Bandits
arXiv:2605.07304v2 Announce Type: replace Abstract: Bandit algorithms solve diverse sequential decision-making problems, but are often too sample-inefficient for from-scratch personalization. To substantially reduce exploration times, latent bandit algorithms exploit cross-instance structure implied by discrete latent states, provided that the posterior distribution of rewards and latent states is known and accurate. However, obtaining an accurate model of this structure is difficult, and a small number of latent states may be insufficient to characterize the reward distributions in all problem instances. We propose latent order bandits (LOB), relaxing the assumptions of latent bandits to require only prior knowledge of a \emph{partial order} of action preferences in each state. This allows instances of the same state to vary in reward distributions, as long as the partial order of actions is shared. For example, groups of users on a streaming service may agree on which movie genres are the best but rate experiences on different scales. We give an upper-confidence bound procedure for the LOB problem, applicable to both total and partial latent orders, and give an upper bound on its regret. To improve empirical performance, we propose a posterior-sampling algorithm and show, in a suite of experiments, that both are competitive with full-prior latent bandits when same-state instances share reward parameters, and preferable to them when reward scales differ between instances with the same latent state.
Abstract:Bandit algorithms solve diverse sequential decision-making problems, but are often too sample-inefficient for from-scratch personalization. To substantially reduce exploration times, latent bandit algorithms exploit cross-instance structure implied by discrete latent states, provided that the posterior distribution of rewards and latent states is known and accurate. However, obtaining an accurate model of this structure is difficult, and a small number of latent states may be insufficient to characterize the reward distributions in all problem instances. We propose latent order bandits (LOB), relaxing the assumptions of latent bandits to require only prior knowledge of a \emph{partial order} of action preferences in each state. This allows instances of the same state to vary in reward distributions, as long as the partial order of actions is shared. For example, groups of users on a streaming service may agree on which movie genres are the best but rate experiences on different scales. We give an upper-confidence bound procedure for the LOB problem, applicable to both total and partial latent orders, and give an upper bound on its regret. To improve empirical performance, we propose a posterior-sampling algorithm and show, in a suite of experiments, that both are competitive with full-prior latent bandits when same-state instances share reward parameters, and preferable to them when reward scales differ between instances with the same latent state.
Machine Learning (cs.LG)
arXiv:2605.07304 [cs.LG]
(or arXiv:2605.07304v2 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2605.07304 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 310 cuvinte
Subiecte conexe
Block Optimism for Nonstationary Bandits with Latent Linear Dynamics
arXiv · 2 oct. 2026
Breaking the Orthogonality Barrier in Quantum LDPC Codes
Quantum Journal · 9 sept. 2026
Latent reasoning architectures would likely undermine CoT, our strongest oversight tool
AI Alignment Forum · 23 sept. 2026
PIRAMID: Progress and Plans
LessWrong · 27 iul. 2026