A two-stage least-squares algorithm combining Christoffel sampling with experimental-design-based allocation of repeated evaluations improves sample complexity for learning noisy conditional expectations.
Adcock , Optimal sampling for least-squares approximation , Foundations of Computational Mathe- matics, (2025), pp
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
stat.ML 1years
2025 1verdicts
ACCEPT 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Hybrid least squares for learning functions from highly noisy data
A two-stage least-squares algorithm combining Christoffel sampling with experimental-design-based allocation of repeated evaluations improves sample complexity for learning noisy conditional expectations.