Совместный семинар HDI lab & TFAIM Lab «Tight Bounds for Schrödinger Potential Estimation in Unpaired Data Translation»

Modern methods of generative modelling and unpaired data translation based on Schrödinger bridges and stochastic optimal control theory aim to transform an initial density to a target one in an optimal way. In the present talk, we assume that we only have access to i.i.d. samples from initial and final distributions. This makes our setup suitable for both generative modelling and unpaired data translation. Relying on the stochastic optimal control approach, we choose an Ornstein-Uhlenbeck process as the reference one and estimate the corresponding Schrödinger potential. Introducing a risk function as the Kullback-Leibler divergence between couplings, we derive tight bounds on generalization ability of an empirical risk minimizer in a class of Schrödinger potentials including Gaussian mixtures. Thanks to the mixing properties of the Ornstein-Uhlenbeck process, we almost achieve fast rates of convergence up to some logarithmic factors in favourable scenarios. We also illustrate performance of the suggested approach with numerical experiments. 

По всем вопросам обращайтесь к Зеленовой Карине Михайловне kzelenova@hse.ru или к Горностаевой Екатерине Дмитриевне egornostaeva@hse.ru