We study the online statistical inference of model parameters in a contextual bandit framework of sequential decision-making.
Dec 30, 2022 · We study the online statistical inference of model parameters in a contextual bandit framework of sequen- tial decision-making. We propose a ...
This work proposes a general framework for online and adaptive data collection environment that can update decision rules via weighted stochastic gradient ...
We study the online statistical inference of model parameters in a contextual bandit framework of sequential decision-making. We propose a general framework for ...
Online statistical inference for contextual bandits via stochastic gradient descent. X Chen, Z Lai, H Li, Y Zhang. arXiv preprint arXiv:2212.14883, 2022. 7 ...
Online statistical inference for contextual bandits via stochastic gradient descent. X Chen, Z Lai, H Li, Y Zhang. arXiv preprint arXiv:2212.14883, 2022. 7 ...
We propose a general framework for online and adaptive data collection environment that can update decision rules via weighted stochastic gradient descent. We ...
... Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent. arXiv, 2022. Academic Service. Journal Reviewer: Annals of Statistics.
Online Statistical Inference for Contextual Bandits via Stochastic Gradient Descent · Computer Science, Mathematics. arXiv.org · 2022.
People also ask
What is the difference between online learning and stochastic gradient descent?
What are the problems with stochastic gradient descent?
Is stochastic gradient descent more accurate?
What is the major difference between using stochastic sub-gradient descent and gradient descent for optimizing perceptron loss?
To this end, we propose a completely online algorithm that can make decisions and update the decision rule online via stochastic gradient descent. It is not ...