AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

Improving Lipschitz-Constrained Neural Networks by Learning Activation Functions

Stanislas Ducotterd, Alexis Goujon, Pakshal Bohra, Dimitris Perdios, Sebastian Neumayer, Michael Unser

JMLR 2024 · Architectures and efficiency › RNNs and normalization · approach: Theory of depth and width

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 learnable LLS activation instead of ReLU1-Lip denoiser · BSD68 (sigma=5/255)PSNR: 36.10 -> 36.86Improved
use LLS instead of AV1-Lip denoiser PnP · single-coil MRI (acc 4)PSNR: 30.61 -> 31.54Improved
use LLS instead of ReLUPnP-FBS · multi-coil MRI PD (acc 4)PSNR: 37.21 -> 38.68Improved
use LLS instead of AVPnP-FBS · CT (noise std 1)PSNR: 34.19 -> 35.15Improved
use LLS instead of ReLU1-Lip Wasserstein GAN discriminator · MNISTinception score: 1.88 -> 2.38Improved
use LLS instead of ReLU1-Lip critic · Gaussian mixtures W1 (N=10)W1 estimate: 5.960 -> 6.486Improved
use LLS instead of GS1-Lip critic · Gaussian mixtures W1 (N=20)W1 estimate: 13.251 -> 13.243No clear effect
add small TV2 regularization lambda=1e-6 to LLS (ablation)LLS denoiser · BSD68 (sigma=5/255)average effective linear regions: 9.24 -> 1.21Improved
add TV2 regularization lambda=1e-6 to LLS (ablation)LLS denoiser · BSD68 (sigma=5/255)PSNR: 36.85 -> 36.86No clear effect
increase TV2 lambda from 1e-6 to 1e-2 (ablation)LLS denoiser · BSD68 (sigma=5/255)PSNR: 36.86 -> 35.15Hurt
increase TV2 lambda to 1e-3 (ablation)LLS denoiser · BSD68 (sigma=5/255)PSNR: 36.86 -> 36.63Hurt
use new LLS implementation (SplineProj parameterization and scaling parameter) instead of old normalization (ablation)LLS 1-Lip network · 1D function fittingtest MSEImproved

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