In non-smooth stochastic convex optimization, a second epoch of SGD with the standard step size can push the population loss up to a constant, and the paper gives matching rates for any step size and step count.
R andom R eshuffling is N ot A lways B etter
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
-
Rapid Overfitting of Multi-Pass Stochastic Gradient Descent in Stochastic Convex Optimization
In non-smooth stochastic convex optimization, a second epoch of SGD with the standard step size can push the population loss up to a constant, and the paper gives matching rates for any step size and step count.