AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Dimensionless machine learning: Imposing exact units equivariance

Soledad Villar, Weichi Yao, David W. Hogg, Ben Blum-Smith, Bianca Dumitrascu

JMLR 2023 · Probabilistic and scientific modeling › Molecules and proteins · approach: Equivariant and disentangled latent representations · 24 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 dimensionless scalar inputs (units equivariance) for the Hamiltonian MLPScalar-based Hamiltonian MLP · Springy double pendulum, Experiment 2 (kg inputs rescaled)state relative error: .3669 -> .0089Improved
use dimensionless scalar inputs (units equivariance) for the Hamiltonian MLPScalar-based Hamiltonian MLP · Springy double pendulum, Experiment 3 (shifted parameter distribution)state relative error: .1885 -> .0435Improved
use dimensionless scalar inputs (units equivariance) for the Hamiltonian MLPScalar-based Hamiltonian MLP · Springy double pendulum, Experiment 1 (in-distribution)state relative error: .0055 -> .0061No clear effect
use dimensionless features in linear regressionRietkerk vegetation linear regression · Rietkerk vegetation regression (held-out test set)test MSE: 26.3 -> 12.6Improved
use dimensionless features in linear regressionRietkerk vegetation linear regression · Rietkerk vegetation regression (held-out test set)Pearson correlation: 0.94 -> 0.97Improved
augment the 286 dimensionless monomials with 500 random dimensional monomials (ablation)Hamiltonian symbolic regression (L2 and LASSO) · Springy pendulum Hamiltonian symbolic regressionheld-out mean-squared error: an order of magnitude worse mean-squared errorHurt
restrict features to dimensionless monomialsHamiltonian symbolic regression · Springy pendulum Hamiltonian symbolic regressionnumber of candidate monomials: 187 500 -> 286Improved
use only dimensionless features when a needed dimensional constant (Planck's h) is missingBlack-body radiation regression · Planck black-body lawfit qualityHurt

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