Stochastic AUC Maximization with Deep Neural Networks

Mingrui Liu, Zhuoning Yuan, Yiming Ying, Tianbao Yang

Keywords:

Mon Session 4 (17:00-19:00 GMT) [Live QA] [Cal]
Mon Session 5 (20:00-22:00 GMT) [Live QA] [Cal]

Abstract: Stochastic AUC maximization has garnered an increasing interest due to better fit to imbalanced data classification. However, existing works are limited to stochastic AUC maximization with a linear predictive model, which restricts its predictive power when dealing with extremely complex data. In this paper, we consider stochastic AUC maximization problem with a deep neural network as the predictive model. Building on the saddle point reformulation of a surrogated loss of AUC, the problem can be cast into a {\it non-convex concave} min-max problem. The main contribution made in this paper is to make stochastic AUC maximization more practical for deep neural networks and big data with theoretical insights as well. In particular, we propose to explore Polyak-\L{}ojasiewicz (PL) condition that has been proved and observed in deep learning, which enables us to develop new stochastic algorithms with even faster convergence rate and more practical step size scheme. An AdaGrad-style algorithm is also analyzed under the PL condition with adaptive convergence rate. Our experimental results demonstrate the effectiveness of the proposed algorithms.

Similar Papers

Towards Better Understanding of Adaptive Gradient Algorithms in Generative Adversarial Nets
Mingrui Liu, Youssef Mroueh, Jerret Ross, Wei Zhang, Xiaodong Cui, Payel Das, Tianbao Yang,
On the Convergence of FedAvg on Non-IID Data
Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang,
Escaping Saddle Points Faster with Stochastic Momentum
Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy,