Introduces a nonparametric identification condition using cyclic monotonicity of the first stage for multivariate IV models with binary instruments, with a corrigendum updating the proof to inverse Brenier maps for more flexible distributions.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
S²R² improves robustness of LoRA-tuned LLMs to prompt perturbations by penalizing semantic-segment drift while preserving clean performance and cross-dataset transfer.
A discrete-time constant flux condition on the heat equation forces the domain to be a ball under suitable regularity.
Under Wasserstein spatial uncertainty the TSP tardiness index scales as Θ(n √(|D|m)/τ) in the interior regime, unlike the classical √n TSP length law.
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
A tractable estimator for functional KL divergence provides a coherent way to compare trajectory inference methods and reveal discrepancies in inferred dynamics from snapshot data.
citing papers explorer
-
A condition for the identification of multivariate models with binary instruments -- with Corrigendum and Addendum
Introduces a nonparametric identification condition using cyclic monotonicity of the first stage for multivariate IV models with binary instruments, with a corrigendum updating the proof to inverse Brenier maps for more flexible distributions.
-
Implicit Neural Optimal Transport via Fixed-Point Optimization
A single-network implicit neural optimal transport method that solves the c-transform via proximal fixed-point iteration for stable, non-adversarial training.
-
Where Do Prompt Perturbations Break Generation? A Segment-Level View of Robustness in LoRA-Tuned Language Models
S²R² improves robustness of LoRA-tuned LLMs to prompt perturbations by penalizing semantic-segment drift while preserving clean performance and cross-dataset transfer.
-
A discrete-time overdetermined problem for the heat equation
A discrete-time constant flux condition on the heat equation forces the domain to be a ball under suitable regularity.
-
Traveling Salesman Tardiness
Under Wasserstein spatial uncertainty the TSP tardiness index scales as Θ(n √(|D|m)/τ) in the interior regime, unlike the classical √n TSP length law.
-
Rectified Flow: A Marginal Preserving Approach to Optimal Transport
A single-objective rectified flow variant uses neural ODEs trained by regression to monotonically decrease a fixed convex transport cost while preserving marginal distributions.
-
Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference
A tractable estimator for functional KL divergence provides a coherent way to compare trajectory inference methods and reveal discrepancies in inferred dynamics from snapshot data.