The non-uniform average of SGD iterates achieves the optimal O(log(1/delta)/T) high-probability error bound on non-smooth strongly convex functions, with a matching lower bound.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Simple and optimal high-probability bounds for strongly-convex stochastic gradient descent
The non-uniform average of SGD iterates achieves the optimal O(log(1/delta)/T) high-probability error bound on non-smooth strongly convex functions, with a matching lower bound.