Simulated annealing with seasonal sliced Wasserstein distance selects climate year subsets that are 2.5-3.5 times more representative than ENTSO-E practice and achieve 4-5 times effective sample size.
The Wasserstein distances
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
A distributional framework for optimizing Lipschitz risk functionals in offline contextual bandits yields data-dependent suboptimality bounds of Õ(1/√n) that match risk-neutral rates and are minimax optimal.
Applies optimal transport to bound OOD generalization error in Transformers via Lipschitz continuity and TC^0 circuit depth lower bounds for Dyck-k backtracking, supported by evaluations on 54 configurations.
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.
citing papers explorer
-
Bridging the climate to energy data gap: simulated annealing for representative climate year selection
Simulated annealing with seasonal sliced Wasserstein distance selects climate year subsets that are 2.5-3.5 times more representative than ENTSO-E practice and achieve 4-5 times effective sample size.
-
Pessimistic Risk-Aware Policy Learning in Contextual Bandits
A distributional framework for optimizing Lipschitz risk functionals in offline contextual bandits yields data-dependent suboptimality bounds of Õ(1/√n) that match risk-neutral rates and are minimax optimal.
-
A Measure-Theoretic Analysis of Reasoning: Structural Generalization and Approximation Limits
Applies optimal transport to bound OOD generalization error in Transformers via Lipschitz continuity and TC^0 circuit depth lower bounds for Dyck-k backtracking, supported by evaluations on 54 configurations.
-
MIRA: A Score for Conditional Distribution Accuracy and Model Comparison
MIRA is a new analytic score for conditional distribution accuracy derived from equal probability mass assignment, enabling Bayesian model comparison via direct posterior validation.