Minimax Lower Bound for Estimating Diffusion-based Local Intrinsic Dimension
This story is from 2026-09-07. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.04822v1 Announce Type: new Abstract: While diffusion-based methods have recently emerged as effective tools for probing the intrinsic geometry of high-dimensional data, their statistical difficulty remains largely unexplored. We study estimation of the finite-scale population functional…
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-09-07 04:00 · arXiv stat.ML
Minimax Lower Bound for Estimating Diffusion-based Local Intrinsic Dimension