Sample complexity of Schrödinger potential estimation
By: Nikita Puchkin , Iurii Pustovalov , Yuri Sapronov and more
Potential Business Impact:
Helps AI learn to create new things better.
We address the problem of Schr\"odinger potential estimation, which plays a crucial role in modern generative modelling approaches based on Schr\"odinger bridges and stochastic optimal control for SDEs. Given a simple prior diffusion process, these methods search for a path between two given distributions $\rho_0$ and $\rho_T^*$ requiring minimal efforts. The optimal drift in this case can be expressed through a Schr\"odinger potential. In the present paper, we study generalization ability of an empirical Kullback-Leibler (KL) risk minimizer over a class of admissible log-potentials aimed at fitting the marginal distribution at time $T$. Under reasonable assumptions on the target distribution $\rho_T^*$ and the prior process, we derive a non-asymptotic high-probability upper bound on the KL-divergence between $\rho_T^*$ and the terminal density corresponding to the estimated log-potential. In particular, we show that the excess KL-risk may decrease as fast as $O(\log^2 n / n)$ when the sample size $n$ tends to infinity even if both $\rho_0$ and $\rho_T^*$ have unbounded supports.
Similar Papers
Tight Bounds for Schrödinger Potential Estimation in Unpaired Image-to-Image Translation Problems
Machine Learning (CS)
Makes pictures look like other pictures.
The Effect of Stochasticity in Score-Based Diffusion Sampling: a KL Divergence Analysis
Machine Learning (CS)
Makes AI art generation more accurate and controllable.
Estimation of discrete distributions in relative entropy, and the deviations of the missing mass
Statistics Theory
Finds hidden patterns in data more accurately.