1. Accelerated Zeroth-Order and First-Order Momentum Methods from Mini to Minimax Optimization.
- Author
-
Feihu Huang, Shangqian Gao, Jian Pei, and Heng Huang
- Subjects
- *
ARTIFICIAL neural networks , *LOGISTIC regression analysis - Abstract
In the paper, we propose a class of accelerated zeroth-order and first-order momentum methods for both nonconvex mini-optimization and minimax-optimization. Specifically, we propose a new accelerated zeroth-order momentum (Acc-ZOM) method for black-box mini-optimization where only function values can be obtained. Moreover, we prove that our Acc-ZOM method achieves a lower query complexity of ~O(d3=4ffl3) for finding an -stationary point, which improves the best known result by a factor of O(d1=4) where d denotes the variable dimension. In particular, our Acc-ZOM does not need large batches required in the existing zeroth-order stochastic algorithms. Meanwhile, we propose an accelerated zeroth-order momentum descent ascent (Acc-ZOMDA) method for black-box minimax optimization, where only function values can be obtained. Our Acc-ZOMDA obtains a low query complexity of ~O((d1 + d2)3=4≤4:5 y ffl3) without requiring large batches for finding an ffl-stationary point, where d1 and d2 denote variable dimensions and ≤y is condition number. Moreover, we propose an accelerated first-order momentum descent ascent (Acc-MDA) method for minimax optimization, whose explicit gradients are accessible. Our Acc-MDA achieves a low gradient complexity of ~O(≤4:5 y ffl3) without requiring large batches for finding an ffl-stationary point. In particular, our Acc-MDA can obtain a lower gradient complexity of O (≤2:5 y ffl3) with a batch size O(≤4 y), which improves the best known result by a factor of O(≤1=2 y). Extensive experimental results on black-box adversarial attack to deep neural networks and poisoning attack to logistic regression demonstrate efficiency of our algorithms. [ABSTRACT FROM AUTHOR]
- Published
- 2022