贝叶斯线性回归

最新推荐文章于 2023-11-15 21:38:34 发布

tony_513

最新推荐文章于 2023-11-15 21:38:34 发布

阅读量138

点赞数

分类专栏：概率论

版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。

本文链接：https://blog.csdn.net/tony_513/article/details/88011650

版权

概率论专栏收录该内容

4 篇文章 0 订阅

订阅专栏

Bayesian Linear Regression youtube video

Why not use MLE? Overfitting!
How to solve?
- Why not use MAP? NO representation of our uncertenty in w and Y

MLE — MLE, blue one is the predict point

baesian linear regression, green line mean uncertenty

Why Bayesian? Optimize loss fn.
- predicive distribution: Given us =what we really want

Setup problem

$D=((x_{1},y_{1}),...,(x_{n},y_{n})),x_{i}\in \mathbb{R}^{d},y_{i}\in \mathbb{R}$

Model: $y_{1},...,y_{n}$ indep given , $y_{i}\sim N(w^{T}x_{i},a^{-1})$ $a = \frac{1}{\sigma^{2}}$ $\sigma$ means variance

$w\sim N(0,b^{-1}I),b>0$ . $(w=(w_{1},...,w_{d}))$ Assume a, b are known $(\theta=w)$

Remark, repalce $x_{i}$ by $\varphi _{i}(x_{i}) = (\varphi _{1}(x_{1}),...,\varphi _{i}(x_{i}))$ ---> Non-linearilites in x by basis function

Likelihood:

$p(D|w)\propto exp(-\frac{1}{2}(y-Aw)^{T}(y-Aw))$

其中， $A = \left ( x_{1}^{T},...,x_{n}^{T} \right )$ "Design Matrix"

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
贝叶斯线性回归

Bayesian Linear Regression youtube videoWhy not use MLE? Overfitting! How to solve? Why not use MAP? NO representation of our uncertenty in w and Y MLE, blue one is the predict pointbaesian li...
复制链接

扫一扫

专栏目录

评论

被折叠的条评论为什么被折叠?

到【灌水乐园】发言

查看更多评论

添加红包

成就一亿技术人!

hope_wisdom

发出的红包

实付元

使用余额支付

点击重新获取

扫码支付

钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。