Refine
Has Fulltext
- no (4)
Document Type
- Article (4) (remove)
Language
- English (4)
Is part of the Bibliography
- yes (4)
Keywords
- confidence sets (2)
- Gaussian sequence model (1)
- High dimensional statistical inference (1)
- Low rank matrices (1)
- Minimax hypothesis testing (1)
- adaptivity (1)
- inverse problem (1)
- limiting distribution (1)
- low rank matrix recovery (1)
- low rank recovery (1)
- matrix completion (1)
- minimax hypothesis testing (1)
- nonasymptotic minimax separation rate (1)
- nuclear norm (1)
- numerical methods (1)
- signal detection (1)
- uncertainty quantification (1)
- unknown variance (1)
Institute
We consider composite-composite testing problems for the expectation in the Gaussian sequence model where the null hypothesis corresponds to a closed convex subset C of R-d. We adopt a minimax point of view and our primary objective is to describe the smallest Euclidean distance between the null and alternative hypotheses such that there is a test with small total error probability. In particular, we focus on the dependence of this distance on the dimension d and variance 1/n giving rise to the minimax separation rate. In this paper we discuss lower and upper bounds on this rate for different smooth and non-smooth choices for C.