LSALSA: accelerated source separation via learned sparse coding

摘要

We propose an efficient algorithm for the generalized sparse coding (SC) inference problem. The proposed framework applies to both the single dictionary setting, where each data point is represented as a sparse combination of the columns of one dictionary matrix, as well as the multiple dictionary setting as given in morphological component analysis (MCA), where the goal is to separate a signal into additive parts such that each part has distinct sparse representation within an appropriately chosen corresponding dictionary. Both the SC task and its generalization via MCA have been cast as \(\ell _1\)-regularized optimization problems of minimizing quadratic reconstruction error. In an effort to accelerate traditional acquisition of sparse codes, we propose a deep learning architecture that constitutes a trainable time-unfolded version of the split augmented lagrangian shrinkage algorithm (SALSA), a special case of the alternating direction method of multipliers (ADMM). We empirically validate both variants of the algorithm, that we refer to as learned-SALSA (LSALSA), on image vision tasks and demonstrate that at inference our networks achieve vast improvements in terms of the running time and the quality of estimated sparse codes on both classic SC and MCA problems over more common baselines. We also demonstrate the visual advantage of our technique on the task of source separation. Finally, we present a theoretical framework for analyzing LSALSA network: we show that the proposed approach exactly implements a truncated ADMM applied to a new, learned cost function with curvature modified by one of the learned parameterized matrices. We extend a very recent stochastic alternating optimization analysis framework to show that a gradient descent step along this learned loss landscape is equivalent to a modified gradient descent step along the original loss landscape. In this framework, the acceleration achieved by LSALSA could potentially be explained by the network’s ability to learn a correction to the gradient direction of steeper descent.