Timezone: »

 
Poster
An inner-loop free solution to inverse problems using deep neural networks
Kai Fan · Qi Wei · Lawrence Carin · Katherine Heller

Tue Dec 05 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #100
in Posters Tue »

We propose a new method that uses deep learning techniques to accelerate the popular alternating direction method of multipliers (ADMM) solution for inverse problems. The ADMM updates consist of a proximity operator, a least squares regression that includes a big matrix inversion, and an explicit solution for updating the dual variables. Typically, inner loops are required to solve the first two sub-minimization problems due to the intractability of the prior and the matrix inversion. To avoid such drawbacks or limitations, we propose an inner-loop free update rule with two pre-trained deep convolutional architectures. More specifically, we learn a conditional denoising auto-encoder which imposes an implicit data-dependent prior/regularization on ground-truth in the first sub-minimization problem. This design follows an empirical Bayesian strategy, leading to so-called amortized inference. For matrix inversion in the second sub-problem, we learn a convolutional neural network to approximate the matrix inversion, i.e., the inverse mapping is learned by feeding the input through the learned forward network. Note that training this neural network does not require ground-truth or measurements, i.e., data-independent. Extensive experiments on both synthetic data and real datasets demonstrate the efficiency and accuracy of the proposed method compared with the conventional ADMM solution using inner loops for solving inverse problems.

Keywords: Computer Vision · Efficient Inference Methods · Signal Processing

Author Information

Kai Fan (Duke University)
Qi Wei (JPMorgan Chase)
Lawrence Carin (Duke University)
Katherine Heller (Duke)

More from the Same Authors