For linear least squares, SNGD and SPRING are proved equivalent to accelerated regularized Kaczmarz methods, yielding the first fast rates and first SPRING guarantee; the general quadratic analysis holds under strong idealized assumptions.
Convergence of variational M onte C arlo simulation and scale-invariant pre-training
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Sketch-and-Project Analysis of Subsampled Natural Gradient Algorithms
For linear least squares, SNGD and SPRING are proved equivalent to accelerated regularized Kaczmarz methods, yielding the first fast rates and first SPRING guarantee; the general quadratic analysis holds under strong idealized assumptions.