AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

A shooting formulation of deep learning

François-Xavier Vialard, Roland Kwitt, Susan Wei, Marc Niethammer

NeurIPS 2020 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Structured continuous-depth models · 4 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 time-dependent parameterization (dynamic) instead of time-constant parameters in UpDown (ablation)UpDown with particles · function approximation y = x^2 + 3/(1+x^2)test loss and network complexityImproved
use static with particles instead of dynamic with particles (ablation)UpDown with particles · function approximation y = x^2 + 3/(1+x^2)test lossHurt
dynamic particle model versus direct models on short snippets of spiral ODE (ablation)UpDown dynamic with particles · spiral ODEtraining and validation lossImproved
use dynamic (time-dependent) UpDown variants instead of static variants (ablation)UpDown · Rotating MNISTMSE at left-out angleNo clear effect
allow time-dependent parameterization (ablation)UpDown · Rotating MNIST latent spacelatent structure (qualitative PCA)Improved
add particle ensemble to static model (ablation)UpDown static · Bouncing ballsper-pixel MSE: 0.0154 -> 0.0150Improved

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