1
Prior Diffusiveness and Regret in the Linear-Gaussian Bandit
Explainpaper上传论文即可高亮陌生术语、AI逐段解析,快速吃透线性高斯Bandit这类复杂数学推导。
arXiv:2601.02022v2 Announce Type: replace Abstract: We prove that Thompson sampling exhibits $\tilde{O}(\sigma d \sqrt{T} + d r \sqrt{\mathrm{Tr}(\Sig…