AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Ode to an ODE

Krzysztof M Choromanski, Jared Quincy Davis, Valerii Likhosherstov, Xingyou Song, Jean-Jacques Slotine, Jacob Varley, Honglak Lee, Adrian Weller, Vikas Sindhwani

NeurIPS 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Expressive invertible architectures · 2 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
replace Dense-1 with ODEtoODE-1ODEtoODE · Corrupted MNIST Stripetest accuracy: 30.55 -> 44.51Improved
replace Dense-1 with ODEtoODE-1ODEtoODE · Corrupted MNIST Dotted Linestest accuracy: 92.99 -> 95.42Improved
replace Dense-1 with ODEtoODE-1ODEtoODE · Corrupted MNIST Glass Blurtest accuracy: 91.62 -> 93.91Improved
replace HyperNet-10 with ODEtoODE-1ODEtoODE · Corrupted MNIST Translatetest accuracy: 29.3 -> 26.82Hurt
replace HyperNet-10 with ODEtoODE-1ODEtoODE · Corrupted MNIST Scaletest accuracy: 68.11 -> 66.68Hurt
increase number of gates from 1 to 10 (ablation)ODEtoODE · Corrupted MNIST Stripetest accuracy: 44.51 -> 44.37No clear effect
increase number of gates from 1 to 10 (ablation)ODEtoODE · Corrupted MNIST Motion Blurtest accuracy: 78.63 -> 77.58Hurt
constant perturbation to hidden units (ODEtoODE-1) works best vs 10 gates (ablation)ODEtoODE · Corrupted MNISTtest accuracyImproved
add dropout 0.1 and width 256 (Table 2 setting) (ablation)ODEtoODE-1 · Corrupted MNIST Stripetest accuracy: 44.51 -> 36.25Hurt
increase NANODE trigonometric degree beyond 5 (ablation)NANODE · RL locomotionrewardHurt
use ODEtoODE policy instead of other architecturesES policy · HumanoidrewardImproved
orthogonal flow vs HyperNet on ES policiesHyperNet · RL tasksrewardHurt

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