Unrolled algorithms for group synchronization
This work addresses a key computational bottleneck in applications like cryo-EM, offering incremental improvements over standard iterative methods.
The paper tackled the group synchronization problem, which involves estimating group elements from noisy pairwise ratios, by applying algorithm unrolling to optimize the estimation process using training data. They demonstrated through numerical experiments that their unrolled algorithms outperform existing methods across various scenarios.
The group synchronization problem involves estimating a collection of group elements from noisy measurements of their pairwise ratios. This task is a key component in many computational problems, including the molecular reconstruction problem in single-particle cryo-electron microscopy (cryo-EM). The standard methods to estimate the group elements are based on iteratively applying linear and non-linear operators, and are not necessarily optimal. Motivated by the structural similarity to deep neural networks, we adopt the concept of algorithm unrolling, where training data is used to optimize the algorithm. We design unrolled algorithms for several group synchronization instances, including synchronization over the group of 3-D rotations: the synchronization problem in cryo-EM. We also apply a similar approach to the multi-reference alignment problem. We show by numerical experiments that the unrolling strategy outperforms existing synchronization algorithms in a wide variety of scenarios.