AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Sparsity in Continuous-Depth Neural Networks

Hananeh Aliee, Till Richter, Mikhail Solonin, Ignacio Ibarra, Fabian J Theis, Niki Kilbertus

NeurIPS 2022 · Probabilistic and scientific modeling › Dynamical systems · approach: Switching and law-discovery dynamics · 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
Add PathReg path-level sparsity instead of unregularized NODENODE · Synthetic second-order ODEextrapolation MSE: 3.2\times 10^{-3} -> 3.9\times10^{-4}Improved
Use L0 regularization instead of no sparsityNODE · Synthetic second-order ODEextrapolation MSE: 3.2\times 10^{-3} -> 3.3\times10^{-2}Hurt
Use LassoNet instead of no sparsityNODE · Synthetic second-order ODEextrapolation MSE: 3.2\times 10^{-3} -> 4.0\times 10^{-2}Hurt
Use GroupLasso (augmented with initial velocities)NODE · Synthetic second-order ODEextrapolation MSE: 3.2\times 10^{-3} -> 1.5\times 10^{-3}Improved
Use PathReg instead of C-NODENODE · Synthetic second-order ODEweight sparsity (%): 16.7 -> 35.2Improved
Add L0 regularizationNODE · MNIST in-distributionaccuracy (%): 97.34 -> 98.36Improved
Add PathRegNODE · MNIST-C mean over corruptionsaccuracy (%): 63.49 -> 69.32Improved
Use L0 instead of PathRegNODE · MNIST-C mean over corruptionsaccuracy (%): 69.32 -> 74.83Improved
Add LassoNetNODE · MNIST-C mean over corruptionsaccuracy (%): 63.49 -> 59.36Hurt
Add PathRegNODE · Human motion capturefeature sparsity (%): 0.0 -> 71.33Improved
Use outer LassoNet instead of inner LassoNetLassoNet · Human motion capturefeature sparsity (%): 7.01 -> 57.48Improved
Use outer LassoNet instead of inner LassoNetLassoNet · Human motion capture walk testMSE: 1.2 \times 10^{-3} -> 8.5 \times 10^{-3}Hurt

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