- 1、本文档共29页,可阅读全部内容。
- 2、有哪些信誉好的足球投注网站(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。
- 3、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
查看更多
Coordinate Descent slide
Coordinate descent
Geoff Gordon Ryan Tibshirani
Optimization 10-725 / 36-725
1
Adding to the toolbox, with stats and ML in mind
We’ve seen several general and useful minimization tools
? First-order methods
? Newton’s method
? Dual methods
? Interior-point methods
These are some of the core methods in optimization, and they are
the main objects of study in this field
In statistics and machine learning, there are a few other techniques
that have received a lot of attention; these are not studied as much
by those purely in optimization
They don’t apply as broadly as above methods, but are interesting
and useful when they do apply ... our focus for the next 2 lectures
2
Coordinate-wise minimization
We’ve seen (and will continue to see) some pretty sophisticated
methods. Today, we’ll see an extremely simple technique that is
surprisingly efficient and scalable
Focus is on coordinate-wise minimization
Q: Given convex, differentiable f : Rn → R, if we are at a point x
such that f(x) is minimized along each coordinate axis, have we
found a global minimizer?
I.e., does f(x+ d · ei) ≥ f(x) for all d, i ? f(x) = minz f(z)?
(Here ei = (0, . . . , 1, . . . 0) ∈ Rn, the ith standard basis vector)
3
x1 x2
f
A: Yes! Proof:
?f(x) =
(
?f
?x1
(x), . . .
?f
?xn
(x)
)
= 0
Q: Same question, but for f convex (not differentiable) ... ?
4
x1
x
2
f
x1
x
2
?4 ?2 0 2 4
?
4
?
2
0
2
4
●
A: No! Look at the above counterexample
Q: Same question again, but now f(x) = g(x) +
∑n
i=1 hi(xi), with
g convex, differentiable and each hi convex ... ? (Non-smooth part
here called separable)
5
x1
x
2
f
x1
x
2
?4 ?2 0 2 4
?
4
?
2
0
2
4
●
A: Yes! Proof: for any y,
f(y)? f(x) ≥ ?g(x)T (y ? x) +
n∑
i=1
[hi(yi)? hi(xi)]
=
n∑
i=1
[?ig(x)(yi ? xi) + hi(yi)? hi(xi)]︸ ︷︷ ︸
≥0
≥ 0
6
Coordinate descent
This suggests that for f(x) = g(x) +
∑n
i=1 hi(xi) (with g convex,
differentiable and each hi convex) we can use coordinate descent
to find a minimizer: start with some initial guess x(0), and repeat
for k = 1, 2, 3, .
您可能关注的文档
- Cell-interactive alginate hydrogels for bone tissue engineering.pdf
- Cell-based approaches to the engineering of vascularized bone tissue.pdf
- Cellular neuropathology.pdf
- CEP8122A单路识别IC.pdf
- cep_procedure_revised_version.pdf
- CertiPUR-US Technical Guidelines 测试.pdf
- CertiPUR-US_Technical_Guidelines_2014.pdf
- CET6 考试听力样题.pdf
- Certipur-us.pdf
- CFA三级私人财富管理.pdf
最近下载
- 履带吊拆卸安装方案.doc
- 如何拍摄公务活动.ppt
- 2024届高三化学一轮复习 说题比赛—2023年高考化学全国新课标卷28题 课件.pptx VIP
- 某医院电动自行车消防安全综合治理工作实施方案.docx VIP
- 探究计算机中的数据表示.docx VIP
- 安全文明工地创优计划(1).doc
- 比亚迪s6维修维修手册(近光灯不亮).pdf VIP
- “线上+线下”混合教学模式在小学心育课中的应用-来源:基础教育参考(第2020011期)-教育部教育管理信息中心.pdf VIP
- SYT 7412-2018-油气长输管道突发事件应急预案编制规范.pdf
- 马克思主义基本原理-华东师范大学-中国大学MOOC慕课答案.pdf
文档评论(0)