AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

InputDSA: Demixing, then comparing recurrent and externally driven dynamics

Ann Huang, Mitchell Ostrow, Satpreet Harcharan Singh, Leo Kozachkov, Ila R Fiete, Kanaka Rajan

ICLR 2026 · Probabilistic and scientific modeling › Dynamical systems · approach: Switching and law-discovery dynamics · 9 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 DMDc with SubspaceDMDc for state distance under partial observation (ablation)InputDSA · Simulated partially observed systems, state distancesilhouette score: 0.68 -> 0.94Improved
replace DMD with SubspaceDMDc for state distance under partial observation (ablation)InputDSA · Simulated partially observed systems, state distancesilhouette score: 0.6 -> 0.94Improved
replace DMDc with SubspaceDMDc for input distance under partial observation (ablation)InputDSA · Simulated partially observed systems, input distancesilhouette score: 0.19 -> 0.83Improved
corrupt the input with noise or polynomial transforms, down to SER near 1 (ablation)InputDSA SubspaceDMDc · Input noise robustnesscorrelation with true-input distances: correlations remain above r > 0.75 as SER approaches 1No clear effect
use surrogate or random inputs instead of ground-truth input (ablation)InputDSA state distance · Random Target Reach RNNscorrelation with ground-truth distancesNo clear effect
use surrogate inputs that correlate more with the true input (e.g. action plus position) (ablation)InputDSA input distance · Random Target Reach RNNscorrelation with ground-truth distancesImproved
compare Top vs Bottom plume agents on input-driven dynamics rather than intrinsic dynamicsInputDSA · Plume Trackinggroup separation of distancesImproved
increase system size from 2 to 1000 dimensions with 2 observed (ablation)SubspaceDMDc state distance · Simulated systemssilhouette scoreHurt

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