AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Online Deep Equilibrium Learning for Regularization by Denoising

Jiaming Liu, Xiaojian Xu, Weijie Gan, Shirin Shoushtari, Ulugbek Kamilov

NeurIPS 2022 · Architectures and efficiency › RNNs and normalization · approach: Differentiable optimization layers · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · IDT, 15 dB input SNRSNR (dB): 40.54 -> 40.57No clear effect
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · Sparse-view CT, 90 viewsSNR (dB): 34.61 -> 34.40Hurt
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · MRI Set1, 10% samplingSNR (dB): 24.10 -> 24.08No clear effect
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · IDT, 20 dB input SNRGPU test time: 6.362s -> 2.051sImproved
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · Sparse-view CT, 180 viewsGPU test time: 5.466s -> 3.113sImproved
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · MRI, 320×320 image, 96 coilsGPU test time: 4.577s -> 3.005sImproved
Use stochastic minibatches of measurements in the DEQ forward and backward passes instead of full-batch measurementsRED (DEQ) · IDT, 20 dB input SNRmeasurement memory per iteration: 3.56 GB -> 0.71 GBImproved
Increase the ODER measurement minibatch from 100 to 250 (ablation)ODER · IDT, 15 dB input SNRSNR (dB): 40.28 -> 40.57Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy