Derives a novel two-point deterministic equivalence for random matrix resolvents to obtain unified asymptotics for SGD-trained linear regression, kernel regression, and random feature models.
Bach, High-dimensional analysis of double descent for linear regression with random projections, SIAM Journal on Mathematics of Data Science6, 26 (2024)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cond-mat.dis-nn 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Two-Point Deterministic Equivalence for Stochastic Gradient Dynamics in Linear Models
Derives a novel two-point deterministic equivalence for random matrix resolvents to obtain unified asymptotics for SGD-trained linear regression, kernel regression, and random feature models.