Disentangling Forced and Internal Climate Variability in Single Realizations using Dynamic Mode Decomposition with Control
2026-07-22T07:23:59Z•dac3645ff8cec0192e164532beedc5c5eaba0e54f381e3b54e19b347c53a9a97
Bayesian-UQBinary-PheNormEHR-phenotypingGaussian-graphical-modelsGlauber-dynamicsPAC-BayesPullbackDMDcalgebraic-statisticsbandit-convex-optimizationclimate-sciencedistributed-classificationdynamic-mode-decompositionimplicit-bias-priorsinexact-scoreslower-boundsmachine-learningmixing-free-algorithmsprobability-tensorsquotient-spacessamplingstatisticstractabilitytransformers','posterior-prefix-tuninguncertainty-quantificationweak-supervision
What happened
Collection of new ML/statistics papers: PullbackDMDc — a DMDc-based method to decompose a single climate realization into forced vs internal variability for attribution and ESM evaluation; two mixing-free algorithms for exact recovery of Gaussian graphical models from a single trajectory of Gaussian Glauber dynamics with optimal dependence on edge strength; a new nontrivial minimax lower bound (˜Ω(d^{5/4}√T)) for stochastic bandit convex optimization; algebraic-signature methods (Kronecker-stack class, MIC) for structural learning in probability tensors; a tight characterization of when in‑/in
Why it matters
A reviewed impact interpretation has not been published for this record.
Evidence and limitations
- Source ID
- arxiv_stat_ml
- Record identifier
- dac3645ff8cec0192e164532beedc5c5eaba0e54f381e3b54e19b347c53a9a97
- Enrichment time
- 2026-07-22T07:23:59Z
- 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.