Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET)
2026-03-31T07:24:01Z•2a9012afc39a0ee5cf4f2451971ab291e2f8cf633aec052896f6be39e1b6077d
Bayes-MICEEDMDKoopman operatorMALA sampler (Metropolis-Adjusted Langevin) ; Random Walk Met],MCMCQ-learningSDE parameter estimationWiener chaos expansionactive statistical inferencebarycenters on graphsdeep matrix factorizationdomain generalizationentropic regularizationfunctional CLTincentive mechanismsintrinsic gradient descentloss landscapeonline statistical inferenceoptimal transportrandom scaling confidence intervalssentinel-auditingstochastic gradient descenttemporal domain driftweight decayzero-retraining adaptation
What happened
ArXiv stat-ml feed (2026-03-31) containing a set of new research papers spanning temporal domain generalization, optimal transport for graph-supported measures, reinforcement-learning inference, stochastic differential-equation parameter estimation, human-AI incentives, loss-landscape theory for regularized deep matrix factorization, Bayesian multiple imputation for time series, uncertainty-aware neural mixture models, distributionally robust optimization with OT costs, and a topological/spectral diagnostic for random matrices. Notable entries: KOMET (Koopman operator identification of model--
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_stat_ml
- Record identifier
- 2a9012afc39a0ee5cf4f2451971ab291e2f8cf633aec052896f6be39e1b6077d
- Enrichment time
- 2026-03-31T07:24:01Z
- AI-assisted enrichment
- Yes
This record may overlap with other records. Its enrichment can be incomplete or wrong, and machine assistance was used. Validate consequential decisions against the linked source and your own environment.