Minibatch SGD with decreasing stochastic Polyak stepsizes keeps iterates bounded under a sublevel-set condition that includes coercive convex objectives, and specific unbounded cases are constructed.
Title resolution pending
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
-
On the boundedness of the sequence generated by minibatch stochastic gradient descent
Minibatch SGD with decreasing stochastic Polyak stepsizes keeps iterates bounded under a sublevel-set condition that includes coercive convex objectives, and specific unbounded cases are constructed.