AI Paper Atlas

Research map / Time series / Causal and generative time series

Neural Stochastic Differential Games for Time-series Analysis

Sungwoo Park, Byoungwoo Park, Moontae Lee, Changhee Lee

ICML 2023 · Time series › Causal and generative time series · approach: Neural differential equations

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
Cooperative multi-agent SDE framework (MaSDEs, trained by deep neural fictitious play) vs. prior DE-based methodstime-series prediction · BAQD, Speech Commands, PhysionetMSE: e.g., BAQD 0.2892 vs 0.3806 for best baseline Latent SDEImproved
Cooperative multi-agent SDE framework vs. prior DE-based methodsMackey-Glass DDE · Mackey-Glass DDERMSE: 0.235 vs 0.272 (CRU)Improved
Cooperative multi-agent SDE framework vs. baselines under out-of-distribution white-noise injectionBAQD with noise level ς=1.0 · BAQD OODMSE (×10^-2): 0.340 vs 0.448 (CRU)Improved
Deep neural fictitious play with cooperative game vs. competitive/zero-sum framingmulti-agent training · theoretical analysisconvergenceNo clear effect
Excluding agent alpha_35 from decision-making (ablation)MaSDEs on BAQD · BAQDprediction performanceHurt
Excluding agent alpha_1 from decision-making (ablation)MaSDEs on BAQD · BAQDprediction performanceNo clear effect

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