Corner Gradient Descent achieves O(t^{-θζ}) loss rates for SGD on power-law spectral problems, with optimal θ = min(2, ν, 2/(ζ+1/ν)).
The option q0 q1 <−1 is inconsistent with condition (65), leaving only the option q0 q1 >−β
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Corner Gradient Descent
Corner Gradient Descent achieves O(t^{-θζ}) loss rates for SGD on power-law spectral problems, with optimal θ = min(2, ν, 2/(ζ+1/ν)).