Deep Online Learning with Stochastic Constraints
This addresses the problem of online learning with multiple objectives for machine learning practitioners, though it appears incremental as it adapts deep learning to a specific scenario.
The paper tackles the challenge of applying deep learning to online tasks with multiple simultaneous loss functions, proposing a novel training procedure that works with any neural network architecture and demonstrating its effectiveness on Neyman-Pearson classification across benchmark datasets.
Deep learning models are considered to be state-of-the-art in many offline machine learning tasks. However, many of the techniques developed are not suitable for online learning tasks. The problem of using deep learning models with sequential data becomes even harder when several loss functions need to be considered simultaneously, as in many real-world applications. In this paper, we, therefore, propose a novel online deep learning training procedure which can be used regardless of the neural network's architecture, aiming to deal with the multiple objectives case. We demonstrate and show the effectiveness of our algorithm on the Neyman-Pearson classification problem on several benchmark datasets.