[其他] 计算视觉Robust and Heavy-Tailed Mean Estimation Made Simple, via Regret Minimization [推广有奖]

0关注
22粉丝

已卖：2001份资源

大师

21%

还不是VIP/贵宾

威望: 1 级
论坛币: 556 个
通用积分: 575.5027
学术水平: 66 点
热心指数: 130 点
信用等级: 37 点
经验: 114069 点
帖子: 6760
精华: 0
在线时间: 2972 小时
注册时间: 2022-8-18
最后登录: 2026-3-6

楼主

2023Hua

发表于 2025-8-11 07:32:39 |AI写论文

是否 +2 论坛币

k人参与回答

经管之家送您一份

应届毕业生专属福利!

求职就业群

赵安豆老师微信：zhaoandou666

经管之家联合CDA

送您一个全额奖学金名额~ !

立即领取

感谢您参与论坛问题回答

经管之家送您两个论坛币！

+2 论坛币

Robust and Heavy-Tailed Mean Estimation Made
      Simple, via Regret Minimization

      Samuel B. Hopkins       Jerry Li       Fred Zhang

                     Abstract
   We study the problem of estimating the mean of a distribution in high dimen-
   sions when either the samples are adversarially corrupted or the distribution is
   heavy-tailed. Recent developments have established efficient and (near) optimal
   procedures for both settings. However, the algorithm ...