arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.16253math.OC
收藏

随机邻近次梯度下降在其积累集附近振荡

Stochastic proximal subgradient descent oscillates in the vicinity of its accumulation set

Sholom Schechtman

摘要:

我们分析的情况下,目标函数是路径可微的随机邻近次梯度下降,并验证了Sard型条件。虽然积累集可能不会减少到唯一的点,我们表明,所花费的时间从一个积累点移动到另一个迭代到无穷大。建立了漂移的振荡型行为。这些结果表明了近似次梯度下降的强稳定性。利用闭测度理论,Bolte、Pauwels和Ríos-Zertuche建立了确定性次梯度下降的这种行为。我们的证明技术依赖于经典的随机逼近的微分包含,这使我们能够扩展结果在确定性的情况下,随机和近端设置,以及以统一的方式对待这些不同的情况下。

英文摘要:

We analyze the stochastic proximal subgradient descent in the case where the objective functions are path differentiable and verify a Sard-type condition. While the accumulation set may not be reduced to unique point, we show that the time spent by the iterates to move from one accumulation point to another goes to infinity. An oscillation-type behavior of the drift is established. These results show a strong stability property of the proximal subgradient descent. Using the theory of closed measures, Bolte, Pauwels and Ríos-Zertuche established this type of behavior for the deterministic subgradient descent. Our technique of proof relies on the classical works on stochastic approximation of differential inclusions, which allows us to extend results in the deterministic case to a stochastic and proximal setting, as well as to treat these different cases in a unified manner.

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。

↑