Discovering Sparse Recovery Algorithms Using Neural Architecture Search
This work addresses the time-consuming and heuristic-driven process of algorithm design for signal processing researchers, though it is incremental as it focuses on rediscovery rather than creating entirely new algorithms.
The paper tackled the challenge of automating algorithm design for inverse problems in signal processing by using Neural Architecture Search (NAS) to rediscover key elements of ISTA and FISTA from a search space of over 50,000 variables, and demonstrated its applicability to other data distributions and algorithms.
The design of novel algorithms for solving inverse problems in signal processing is an incredibly difficult, heuristic-driven, and time-consuming task. In this short paper, we the idea of automated algorithm discovery in the signal processing context through meta-learning tools such as Neural Architecture Search (NAS). Specifically, we examine the Iterative Shrinkage Thresholding Algorithm (ISTA) and its accelerated Fast ISTA (FISTA) variant as candidates for algorithm rediscovery. We develop a meta-learning framework which is capable of rediscovering (several key elements of) the two aforementioned algorithms when given a search space of over 50,000 variables. We then show how our framework can apply to various data distributions and algorithms besides ISTA/FISTA.