MB-SARAH-RBB uses a random Barzilai-Borwein step size to accelerate mini-batch SARAH, with a linear convergence proof and improved complexity for strongly convex objectives.
Li, Preconditioned stochastic gradient descent , IEEE Transactions on Neural Networks and Learning Systems 29 (5) (2018) 1454–1 466
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Accelerating Mini-batch SARAH by Step Size Rules
MB-SARAH-RBB uses a random Barzilai-Borwein step size to accelerate mini-batch SARAH, with a linear convergence proof and improved complexity for strongly convex objectives.