Extends BLASSO to multivariate GMMs with component-specific unknown diagonal covariances and derives non-asymptotic recovery guarantees under an explicit separation condition using Fisher-Rao geometry.
We have |g− 1/ 2 bkbk ∂bkKnorm(x,x ′)| ≤ √ d∏ l=1 Knorm(xl,x ′ l) ⏐ ⏐ ⏐ ⏐ √ Knorm(xk,x ′ k) − 1 g− 1/ 2 bkbk ∂bkKnorm(xk,x ′ k) ⏐ ⏐ ⏐ ⏐
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.ST 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Gaussian Mixture Model with unknown diagonal covariances via continuous sparse regularization
Extends BLASSO to multivariate GMMs with component-specific unknown diagonal covariances and derives non-asymptotic recovery guarantees under an explicit separation condition using Fisher-Rao geometry.