Stochastic AUC Maximization with Deep Neural Networks
This work addresses imbalanced data classification for machine learning practitioners by making stochastic AUC maximization more practical with deep neural networks, though it is incremental as it builds on existing saddle point reformulations.
The paper tackles the problem of stochastic AUC maximization for imbalanced data classification by extending it to deep neural networks, proposing new algorithms with faster convergence rates and more practical step sizes, and demonstrating their effectiveness experimentally.
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-Łojasiewicz (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.