Establishes a unified temporal-spatial minimax lower bound of order M to the power of minus gamma_d times (k+1) over (k+1 plus gamma_d) for W2-risk of future distribution estimates under k-th order adiabatic smoothness on the velocity field.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Two-parameter flows learn base-to-marginal transports via conditional flow matching then extract unique physics-time velocities by regression on synthetic trajectories, inheriting regularity and scaling to high dimensions while permitting non-gradient dynamics.
Presents a drift transformation framework for multidimensional diffusions that yields product-form transition densities, with explicit results for Wiener and Ornstein-Uhlenbeck cases including resetting and stochastic ordering.
citing papers explorer
-
Two-Parameter Flows for Learning Population Dynamics of Physical Systems
Two-parameter flows learn base-to-marginal transports via conditional flow matching then extract unique physics-time velocities by regression on synthetic trajectories, inheriting regularity and scaling to high dimensions while permitting non-gradient dynamics.