| Title | Decentralized Min-Max Optimization: Formulations, Algorithms and Applications in Network Poisoning Attack |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Tsaknakis, Ioannis, Hong, Mingyi, Liu, Sijia |
| Conference Name | ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) |
| Date Published | may |
| Keywords | AI Poisoning, convergence, Distributed optimization, Human Behavior, machine learning, machine learning algorithms, min-max optimization, Optimization, poisoning attack, pubcrawl, Resiliency, Scalability, Signal processing algorithms, speech processing, Training |
| Abstract | This paper discusses formulations and algorithms which allow a number of agents to collectively solve problems involving both (non-convex) minimization and (concave) maximization operations. These problems have a number of interesting applications in information processing and machine learning, and in particular can be used to model an adversary learning problem called network data poisoning. We develop a number of algorithms to efficiently solve these non-convex min-max optimization problems, by combining techniques such as gradient tracking in the decentralized optimization literature and gradient descent-ascent schemes in the min-max optimization literature. Also, we establish convergence to a first order stationary point under certain conditions. Finally, we perform experiments to demonstrate that the proposed algorithms are effective in the data poisoning attack. |
| DOI | 10.1109/ICASSP40776.2020.9054056 |
| Citation Key | tsaknakis_decentralized_2020 |
Decentralized Min-Max Optimization: Formulations, Algorithms and Applications in Network Poisoning Attack