Learning to optimize (L2O) stands at the intersection of traditional optimization and machine
learning, utilizing the capabilities of machine learning to enhance conventional optimization …

In recent years, there have been significant advances in the use of deep learning methods in
inverse problems such as denoising, compressive sensing, inpainting, and super-resolution …

Based on the dynamic model, a robust constrained control method for permanent magnet
synchronous motor (PMSM) is proposed in this paper to achieve better trajectory tracking …

Model-based neural networks provide unparalleled performance for various tasks, such as
sparse coding and compressed sensing problems. Due to the strong connection with the …

We present a new deep unfolding network for analysis-sparsity-based Compressed
Sensing. The proposed network coined Decoding Network (DECONET) jointly learns a …

Solving linear inverse problems plays a crucial role in numerous applications. Algorithm
unfolding based, model-aware data-driven approaches have gained significant attention for …

Much of Bayesian inference centers around the design of estimators for inverse problems
which are optimal assuming the data comes from a known prior. But what do these optimality …

Analog beamforming is the predominant approach for millimeter wave (mmWave)
communication given its favor-able characteristics for limited-resource devices. In this work …

Recently, deep neural networks (DNNs) have become powerful tools for solving inverse
scattering problems. However, the approximation and generalization rates of DNNs for …

Learning to Optimize: Algorithm Unrolling Page 1 Learning to Optimize: Algorithm Unrolling
Wotao Yin Decision Intelligence Lab, DAMO Academy Alibaba Group US CVPR Tutorial …