High-probability ergodic and last-iterate complexity guarantees for random reshuffling SGD on smooth nonconvex optimization that match best in-expectation bounds up to logarithmic factors without extra assumptions.
Incremental subgradient methods for nondifferentiable optimization
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
math.OC 1years
2023 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
High Probability Guarantees for Random Reshuffling
High-probability ergodic and last-iterate complexity guarantees for random reshuffling SGD on smooth nonconvex optimization that match best in-expectation bounds up to logarithmic factors without extra assumptions.