Efficient Generalized Low-Rank Tensor Contextual Bandits

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yi, Qianxin, Yang, Yiyang, Tang, Shaojie, Liu, Jiapeng, Wang, Yao
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916093893804032
author Yi, Qianxin
Yang, Yiyang
Tang, Shaojie
Liu, Jiapeng
Wang, Yao
author_facet Yi, Qianxin
Yang, Yiyang
Tang, Shaojie
Liu, Jiapeng
Wang, Yao
contents 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 high-usable and accountable decision-making services. To this end, we introduce a generalized low-rank tensor contextual bandits model in which an action is formed from three feature vectors, and thus can be represented by a tensor. In this formulation, the reward is determined through a generalized linear function applied to the inner product of the action's feature tensor and a fixed but unknown parameter tensor with a low tubal rank. To effectively achieve the trade-off between exploration and exploitation, we introduce a novel algorithm called "Generalized Low-Rank Tensor Exploration Subspace then Refine" (G-LowTESTR). This algorithm first collects raw data to explore the intrinsic low-rank tensor subspace information embedded in the decision-making scenario, and then converts the original problem into an almost lower-dimensional generalized linear contextual bandits problem. Rigorous theoretical analysis shows that the regret bound of G-LowTESTR is superior to those in vectorization and matricization cases. We conduct a series of simulations and real data experiments to further highlight the effectiveness of G-LowTESTR, leveraging its ability to capitalize on the low-rank tensor structure for enhanced learning.
format Preprint
id arxiv_https___arxiv_org_abs_2311_01771
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Efficient Generalized Low-Rank Tensor Contextual Bandits
Yi, Qianxin
Yang, Yiyang
Tang, Shaojie
Liu, Jiapeng
Wang, Yao
Machine Learning
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 high-usable and accountable decision-making services. To this end, we introduce a generalized low-rank tensor contextual bandits model in which an action is formed from three feature vectors, and thus can be represented by a tensor. In this formulation, the reward is determined through a generalized linear function applied to the inner product of the action's feature tensor and a fixed but unknown parameter tensor with a low tubal rank. To effectively achieve the trade-off between exploration and exploitation, we introduce a novel algorithm called "Generalized Low-Rank Tensor Exploration Subspace then Refine" (G-LowTESTR). This algorithm first collects raw data to explore the intrinsic low-rank tensor subspace information embedded in the decision-making scenario, and then converts the original problem into an almost lower-dimensional generalized linear contextual bandits problem. Rigorous theoretical analysis shows that the regret bound of G-LowTESTR is superior to those in vectorization and matricization cases. We conduct a series of simulations and real data experiments to further highlight the effectiveness of G-LowTESTR, leveraging its ability to capitalize on the low-rank tensor structure for enhanced learning.
title Efficient Generalized Low-Rank Tensor Contextual Bandits
topic Machine Learning
url https://arxiv.org/abs/2311.01771