On high-dimensional and low-rank tensor bandits
Most existing studies on linear bandits focus on a one-dimensional characterization of the
overall system. While being representative, this formulation may fail to model applications …
overall system. While being representative, this formulation may fail to model applications …
Low-Rank Online Dynamic Assortment with Dual Contextual Information
SJ Lee, WW Sun, Y Liu - arXiv preprint arXiv:2404.17592, 2024 - arxiv.org
As e-commerce expands, delivering real-time personalized recommendations from vast
catalogs poses a critical challenge for retail platforms. Maximizing revenue requires careful …
catalogs poses a critical challenge for retail platforms. Maximizing revenue requires careful …
Efficient Generalized Low-Rank Tensor Contextual Bandits
Q Yi, Y Yang, Y Wang, S Tang - arXiv preprint arXiv:2311.01771, 2023 - arxiv.org
In this paper, we aim to build a novel bandits algorithm that is capable of fully harnessing the
power of multi-dimensional data and the inherent non-linearity of reward functions to provide …
power of multi-dimensional data and the inherent non-linearity of reward functions to provide …
ONLINE STATISTICAL INFERENCE FOR LOW-RANK REINFORCEMENT LEARNING
Q Han - 2024 - hammer.purdue.edu
We propose a fully online procedure to conduct statistical inference with adaptively collected
data. The low-rank structure of the model parameter and the adaptivity nature of the data …
data. The low-rank structure of the model parameter and the adaptivity nature of the data …