Robust Latent Variable Graphical Models: Exact Recovery and Fundamental Limits
arXiv:2610.27010v1 Announce Type: new Abstract: We study robust estimation of a Gaussian precision matrix that decomposes as a sparse matrix minus a symmetric, possibly indefinite, low-rank matrix, a structure that arises when latent-variable marginalization is combined with conditioning on linear…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-10-21 04:00 · arXiv stat.ML
Robust Latent Variable Graphical Models: Exact Recovery and Fundamental Limits