On the Complexity of Finding Small Subgradients in Nonsmooth Optimization
On the Complexity of Finding Small Subgradients in Nonsmooth Optimization
复制标题
关于非光滑优化中寻找小次梯度的复杂性
DOI:
10.48550/arxiv.2209.10346
复制
发表时间:
2022
期刊:
影响因子:
--
通讯作者:
Ohad Shamir
中科院分区:
文献类型:
--
作者:
Guy Kornowski;Ohad Shamir
We study the oracle complexity of producing $(\delta,\epsilon)$-stationary points of Lipschitz functions, in the sense proposed by Zhang et al. [2020]. While there exist dimension-free randomized algorithms for producing such points within $\widetilde{O}(1/\delta\epsilon^3)$ first-order oracle calls, we show that no dimension-free rate can be achieved by a deterministic algorithm. On the other hand, we point out that this rate can be derandomized for smooth functions with merely a logarithmic dependence on the smoothness parameter. Moreover, we establish several lower bounds for this task which hold for any randomized algorithm, with or without convexity. Finally, we show how the convergence rate of finding $(\delta,\epsilon)$-stationary points can be improved in case the function is convex, a setting which we motivate by proving that in general no finite time algorithm can produce points with small subgradients even for convex functions.
DOI:
--
发表时间:
2021-12
期刊:
--
影响因子:
--
作者:
Damek Davis;D. Drusvyatskiy;Y. Lee;Swati Padmanabhan;Guanghao Ye
通讯作者:
Damek Davis;D. Drusvyatskiy;Y. Lee;Swati Padmanabhan;Guanghao Ye
DOI:
--
发表时间:
2020-03
期刊:
ArXiv
影响因子:
--
作者:
Y. Carmon;A. Jambulapati;Qijia Jiang;Yujia Jin;Y. Lee;Aaron Sidford;Kevin Tian
通讯作者:
Y. Carmon;A. Jambulapati;Qijia Jiang;Yujia Jin;Y. Lee;Aaron Sidford;Kevin Tian