Abstract | ||
---|---|---|
Zeroth-order optimization or derivative-free optimization is an important research topic in machine learning. In recent, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract Hessian information of the model function. In this paper, we utilize the second-order information of the objective function and propose a novel emph{Hessian-aware zeroth-order algorithm} called texttt{ZO-HessAware}. Our theoretical result shows that texttt{ZO-HessAware} has an improved zeroth-order convergence rate and query complexity under structured Hessian approximation, where we propose a few approximation methods of such. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity. |
Year | Venue | DocType |
---|---|---|
2018 | arXiv: Learning | Journal |
Volume | Citations | PageRank |
abs/1812.11377 | 1 | 0.37 |
References | Authors | |
18 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haishan Ye | 1 | 12 | 6.63 |
Zhichao Huang | 2 | 1 | 1.38 |
Cong Fang | 3 | 17 | 7.14 |
Chris Junchi Li | 4 | 5 | 1.11 |
Zhang, Tong | 5 | 7126 | 611.43 |