AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Identifiable Smooth Conjugacy Learning via Adversarial Orthogonality

In Huh, Changwook Jeong, Muhammad Alam

ICML 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Physics-informed dynamics learning

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 adversarial orthogonality regularizer to context modulation (ablation)CM conjugacy · Hopf normal formdH: 0.142 -> 0.081Improved
add adversarial orthogonality to context modulationCM conjugacy · Hopf observed spacedH: 0.064 -> 0.064No clear effect
allow source correction (CM, Aug., DT) instead of fixed sourcebaseline conjugacy · Hopf observed spacedH: 0.547 -> 0.064Improved
add orthogonality regularizerCM conjugacy · Duffing oscillatorZ2 symmetry / test MSEImproved
add orthogonality regularizer (ablation)CM conjugacy · Hopf extrapolationdH (normal form): 0.177 -> 0.103Improved
add orthogonality regularizer (ablation)CM conjugacy · FitzHugh-Nagumo omega=2 canonicalMSE: 0.703 -> 0.218Improved
use direct tuning or L2-SP of source weightsconjugacy learning · FitzHugh-Nagumo omega=1 canonicalMSE: 2.199 -> 199.0Hurt
use less expressive NICE adversary instead of Real NVP (ablation)CM-AO · Hopf normal formdH: 0.081 -> 0.093Hurt
use CNF adversary instead of Real NVP (ablation)CM-AO · Hopf normal formdH: 0.081 -> 0.075No clear effect
increase lambda_orth to 1e-2 (ablation)CM-AO · Hopf normal formMMD: 0.109 -> 0.304Hurt
use hinge-loss variant at lambda_orth 1e-2 (ablation)CM-AO · Hopf normal formMMD: 0.304 -> 0.106Improved
moderate lambda_orth between 1e-4 and 3e-3 (ablation)CM-AO · Hopf normal formdH: 0.142 -> 0.071Improved

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