4 citations · 4 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2023
Almost Sure Saddle Avoidance of Stochastic Gradient Methods without the Bounded Gradient Assumption
Jun Liu, Ye Yuan
We prove that various stochastic gradient descent methods, including the stochastic gradient descent (SGD), stochastic heavy-ball (SHB), and stochastic Nesterov's accelerated gradi…
cs.LG2022★ 4 cited
On Almost Sure Convergence Rates of Stochastic Gradient Methods
Jun Liu, Ye Yuan
The vast majority of convergence rates analysis for stochastic gradient methods in the literature focus on convergence in expectation, whereas trajectory-wise almost sure convergen…