Frank-Wolfe Network: An Interpretable Deep Structure for Non-Sparse Coding

TL;DR

The paper introduces Frank-Wolfe Network (F-W Net), an interpretable deep architecture inspired by the Frank-Wolfe algorithm for non-sparse $L_p$-norm constrained coding, with learnable $p$ and applications in image processing.

Contribution

It proposes a novel deep network architecture based on unrolling the Frank-Wolfe algorithm for $L_p$-norm constrained coding, including a learnable $p$ parameter and a convolutional variant for image tasks.

Findings

F-W Net effectively solves non-sparse coding problems.

The learnable $p$ parameter enhances flexibility and performance.

F-W Net performs well in digit recognition, denoising, and super-resolution.

Abstract

The problem of $L_p$-norm constrained coding is to convert signal into code that lies inside an $L_p$-ball and most faithfully reconstructs the signal. Previous works under the name of sparse coding considered the cases of $L_0$ and $L_1$ norms. The cases with $p>1$ values, i.e. non-sparse coding studied in this paper, remain a difficulty. We propose an interpretable deep structure namely Frank-Wolfe Network (F-W Net), whose architecture is inspired by unrolling and truncating the Frank-Wolfe algorithm for solving an $L_p$-norm constrained problem with $p\geq 1$. We show that the Frank-Wolfe solver for the $L_p$-norm constraint leads to a novel closed-form nonlinear unit, which is parameterized by $p$ and termed $pool_p$. The $pool_p$ unit links the conventional pooling, activation, and normalization operations, making F-W Net distinct from existing deep networks either heuristically designed or converted from projected gradient descent algorithms. We further show that the hyper-parameter $p$ can be made learnable instead of pre-chosen in F-W Net, which gracefully solves the non-sparse coding problem even with unknown $p$. We evaluate the performance of F-W Net on an extensive range of simulations as well as the task of handwritten digit recognition, where F-W Net exhibits strong learning capability. We then propose a convolutional version of F-W Net, and apply the convolutional F-W Net into image denoising and super-resolution tasks, where F-W Net all demonstrates impressive effectiveness, flexibility, and robustness.