一阶低秩无启示和倾向启示的Optimization算法的比较
Comparison of an Apocalypse-Free and an Apocalypse-Prone First-Order Low-Rank Optimization Algorithm
摘要:
我们比较了两种一阶低秩优化算法,即$\text{P}^2\text{GD}$(Schneider和Uschmajew,2015),它已被证明是倾向于启示录的(Levin等人,2021),以及其无启示录版本$\text{P}^2\text{GDR}$,其通过为$\text{P}^2\text{GD}$配备合适的秩缩减机制而获得(Olikier等人,2022年)。这里的启示是指平稳性措施的情况下,沿收敛序列为零,而它是非零的极限。比较是在两个简单的启示的例子,原来的一个(莱文等人,2021年,一个新的。我们还提出了一个潜在的副作用的秩减少机制的$\text{P}^2\text{GDR}$和讨论的秩减少参数的选择。
英文摘要:
We compare two first-order low-rank optimization algorithms, namely $\text{P}^2\text{GD}$ (Schneider and Uschmajew, 2015), which has been proven to be apocalypse-prone (Levin et al., 2021), and its apocalypse-free version $\text{P}^2\text{GDR}$ obtained by equipping $\text{P}^2\text{GD}$ with a suitable rank reduction mechanism (Olikier et al., 2022). Here an apocalypse refers to the situation where the stationarity measure goes to zero along a convergent sequence whereas it is nonzero at the limit. The comparison is conducted on two simple examples of apocalypses, the original one (Levin et al., 2021) and a new one. We also present a potential side effect of the rank reduction mechanism of $\text{P}^2\text{GDR}$ and discuss the choice of the rank reduction parameter.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。