Deep neural networks are the state-of-the-art for various applications. However,one of the biggest challenges facing them is the lack of labeled data to train these complex networks.

We introduce Policy Optimization with Multiple Optima (POMO), anend-to-end approach forbuildingsuchaheuristic solver.POMO isapplicable to a wide range of CO problems.

Specifically, instead of directly measuring the divergence with paired images, we train a reward model with the dataset we construct, consisting of nearly 51,000 images annotated with human preferences.

More challenging computational imaging applications, such as3D snapshot microscopywhichcompresses 3Dvolumes intosingle2Dimages, require ahighly non-local optical encoder. We show that existing deep network decoders have a locality bias which prevents the optimization of such highly non-local optical encoders. We address this with a decoder based on a shallow neural network architecture using global kernel Fourier convolutional neural networks (FourierNets).

Mathematically characterizing the implicit regularization induced by gradientbased optimization is a longstanding pursuit in the theory of deep learning. A widespread hope isthatacharacterization based onminimization ofnorms may apply, and a standard test-bed for studying this prospect is matrix factorization (matrix completion via linear neural networks). It is an open question whether normscanexplaintheimplicit regularization inmatrixfactorization.

Federated Learning (PFL) has emerged, where personalized models are trained for individual clients.