We study the basic statistical problem of testing whether normally distributed n -dimensional data has been truncated , i.e., altered by only retaining points that lie in some unknown truncation set S \subseteq \mathbb{R}^{n} . As our main algorithmic results, Both our algorithms are computationally efficient and run in O(n^{2}) time, which is linear in the size of the input. These results stand in sharp contrast with known results for learning or testing convex bodies with respect to the normal distribution or learning convex-truncated normal distributions, where state-of-the-art algorithms require essentially n^{O(\sqrt{n})} samples. An easy argument shows that no finite number of samples suffices to distinguish N(0,I_{n}) from an unknown and arbitrary mixture of general (not necessarily symmetric) convex sets, so no common generalization of results (1) and (2) above is possible. We also prove that any algorithm (computationally efficient or otherwise) that can distinguish N(0,I_{n}) from N(0,I_{n}) conditioned on an unknown symmetric convex set must use \Omega(n) samples. This shows that the sample complexity of each of our algorithms is optimal up to a constant factor.
Read full abstract- All Solutions
Editage
One platform for all researcher needs
Paperpal
AI-powered academic writing assistant
R Discovery
Your #1 AI companion for literature search
Mind the Graph
AI tool for graphics, illustrations, and artwork
Journal finder
AI-powered journal recommender
Unlock unlimited use of all AI tools with the Editage Plus membership.
Explore Editage Plus - Support
Overview
10444 Articles
Published in last 50 years
Articles published on Basic Problems
Authors
Select Authors
Journals
Select Journals
Duration
Select Duration
11582 Search results
Sort by Recency