Original Pdf: pdf
Keywords: determinantal point processes, deep learning, optimization
TL;DR: We proposed a specific back-propagation method via proper spectral sub-gradient to integrate determinantal point process to deep learning framework.
Abstract: Determinantal point processes (DPPs) is an effective tool to deliver diversity on multiple machine learning and computer vision tasks. Under deep learning framework, DPP is typically optimized via approximation, which is not straightforward and has some conflict with diversity requirement. We note, however, there has been no deep learning paradigms to optimize DPP directly since it involves matrix inversion which may result in highly computational instability. This fact greatly hinders the wide use of DPP on some specific objectives where DPP serves as a term to measure the feature diversity. In this paper, we devise a simple but effective algorithm to address this issue to optimize DPP term directly expressed with L-ensemble in spectral domain over gram matrix, which is more flexible than learning on parametric kernels. By further taking into account some geometric constraints, our algorithm seeks to generate valid sub-gradients of DPP term in case when the DPP gram matrix is not invertible (no gradients exist in this case). In this sense, our algorithm can be easily incorporated with multiple deep learning tasks. Experiments show the effectiveness of our algorithm, indicating promising performance for practical learning problems.