当前位置:网站首页>ICML 2022 | meta proposes a robust multi-objective Bayesian optimization method to effectively deal with input noise
ICML 2022 | meta proposes a robust multi-objective Bayesian optimization method to effectively deal with input noise
2022-07-04 20:26:00 【Zhiyuan community】
Thesis link :
https://arxiv.org/abs/2202.07549
Project links :
https://github.com/facebookresearch/robust_mobo
This article is about facebook Published in ICML 2022 A piece of work for , It theoretically analyzes the multi-objective Bayesian Optimization with input noise .
This paper deals with the input noise problem of multi-objective optimization , Combined with Bayesian Optimization and Pareto optimization, the global multi-objective VaR is designed and optimized , To solve the problem of black box constraint sensitive to input noise . Bayesian optimization by adjusting design parameters , Black box performance indicators with high evaluation cost can be optimized . Although many methods have been proposed to optimize a single target under input noise , However, there is still a lack of methods to solve the practical problem that multiple targets are sensitive to input disturbances .
In this work , The author proposes the first robust multi-objective Bayesian optimization method to deal with input noise . The author formalizes the goal as a risk measure to optimize an uncertain goal , That is, multivariable value at risk (MVaR). Due to direct optimization MVaR In many cases, it is computationally infeasible , The author proposes an extensible 、 A theory based approach to use random scales to optimize MVaR. Experimentally speaking , This method is significantly better than other methods in data set , And effectively realize the optimal Luban design .
边栏推荐
- Employment prospects and current situation of Internet of things application technology
- Application practice | Shuhai supply chain construction of data center based on Apache Doris
- Lingyun going to sea | Wenhua online & Huawei cloud: creating a new solution for smart teaching in Africa
- Neural network IOT platform construction (IOT platform construction practical tutorial)
- Delete the characters with the least number of occurrences in the string [JS, map sorting, regular]
- YOLOv5s-ShuffleNetV2
- 输入的查询SQL语句,是如何执行的?
- 为什么最大速度是光速
- 九齐单片机NY8B062D单按键控制4种LED状态
- Development and construction of DFI ecological NFT mobile mining system
猜你喜欢
Free soldier
Actual combat simulation │ JWT login authentication
In the first month of its launch, the tourist praise rate of this campsite was as high as 99.9%! How did he do it?
The company needs to be monitored. How do ZABBIX and Prometheus choose? That's the right choice!
输入的查询SQL语句,是如何执行的?
多表操作-外连接查询
What are the consequences of closing the read / write channel?
上线首月,这家露营地游客好评率高达99.9%!他是怎么做到的?
What should we pay attention to when doing social media marketing? Here is the success secret of shopline sellers!
实战模拟│JWT 登录认证
随机推荐
BCG 使用之CBCGPProgressDlgCtrl進度條使用
Huawei cloud store homepage banner resource bit application
Utilisation de la barre de progression cbcggprogressdlgctrl utilisée par BCG
Oracle database, numbers Force 2 decimal places to display-Alibaba Cloud
1006 sign in and sign out (25 points) (PAT class a)
Taishan Office Technology Lecture: about the order of background (shading and highlighting)
C语言-入门-基础-语法-流程控制(七)
【毕业季】绿蚁新醅酒,红泥小火炉。晚来天欲雪,能饮一杯无?
Data set division
AP8022开关电源小家电ACDC芯片离线式开关电源IC
Qt编写物联网管理平台38-多种数据库支持
kotlin 继承
Template_ Judging prime_ Square root / six prime method
15million employees are easy to manage, and the cloud native database gaussdb makes HR office more efficient
TCP waves twice, have you seen it? What about four handshakes?
QT writing the Internet of things management platform 38- multiple database support
Siemens HMI download prompts lack of panel image solution
一文搞懂Go语言中文件的读写与创建
软件客户端数字签名一定要申请代码签名证书吗?
YOLOv5s-ShuffleNetV2