欢迎光临!
您现在所在的位置:首页 >> 通知公告 & 学术信息
学术信息
SEMINARS
Sparse Grid Meets Random Hashing: Learning High Dimensional Functions of Few Variables
时间  Datetime
2019-01-15 16:00 — 17:30 
地点  Venue
Middle Lecture Room
报告人  Speaker
Ming Yuan
单位  Affiliation
Dept. of Statistics, Columbia University
邀请人  Host
Dept. of Statistics
报告摘要  Abstract

We investigate the optimal sample complexity of recovering a general high dimensional smooth and sparse function based on point queries. Our results provides a precise characterization of the potential loss in information when restricting to point queries as opposed to the more general linear queries, as well as the benefit of adaption. In addition, we also developed a general framework for function approximation to mitigate the curse of dimensionality that can also be easily adapted to incorporate further structure such as lower order interactions, leading to sample complexities better than those obtained earlier in the literature.