Regularized deep learning with nonconvex penalties
This work addresses regularization for deep learning practitioners, but it is incremental as it builds on existing nonconvex penalty methods.
The paper tackled the problem of overfitting in deep neural networks by exploring nonconvex penalties for regularization, showing that these penalties perform well with standard optimization algorithms and assessing their performance on seven datasets.
Regularization methods are often employed in deep learning neural networks (DNNs) to prevent overfitting. For penalty based DNN regularization methods, convex penalties are typically considered because of their optimization guarantees. Recent theoretical work have shown that nonconvex penalties that satisfy certain regularity conditions are also guaranteed to perform well with standard optimization algorithms. In this paper, we examine new and currently existing nonconvex penalties for DNN regularization. We provide theoretical justifications for the new penalties and also assess the performance of all penalties with DNN analyses of seven datasets.