New 'Manifold-Index Model' claims provable escape from curse of dimensionality in regression
A new paper introduces the Manifold-Index Model for vector-valued regression where predictors lie in a tube around an unknown m-dimensional manifold in R^D, with proofs of avoiding statistical and computational curse of dimensionality.
Read the full story at arXiv stat.ML ↗
Timeline · 1 report
- 2026-11-17 05:00 · arXiv stat.ML
The Manifold-Index Model: provably and efficiently avoiding the statistical and computational curse of dimensionality