Finite-Time Analysis of Discrete-Time Stochastic Interpolants
The stochastic interpolant framework offers a powerful approach for constructing generative models based on ordinary differential equations (ODEs) or stochastic differential equations (SDEs) to transform arbitrary data distributions. However, prior analyses of this framework have primarily focused on the continuous-time setting, assuming a perfect solution of the underlying equations. In this work, we present the first discrete-time analysis of the stochastic interpolant framework, where we introduce an innovative discrete-time sampler and derive a finite-time upper bound on its distribution estimation error. Our result provides a novel quantification of how different factors, including the distance between source and target distributions and estimation accuracy, affect the convergence rate and also offers a new principled way to design efficient schedules for convergence acceleration. Finally, numerical experiments are conducted on the discrete-time sampler to corroborate our theoretical findings.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reachability and Controllability Analysis of the State Covariance for Linear Stochastic Systems
This paper studies the set of terminal state covariances that are reachable over a finite time horizon from a given initial state covariance for a linear stochastic system with additive noise. For discrete-time systems, …
Moment Propagation of Discrete-Time Stochastic Polynomial Systems using Truncated Carleman Linearization
We propose a method to compute an approximation of the moments of a discrete-time stochastic polynomial system. We use the Carleman linearization technique to transform this finite-dimensional polynomial system into an i…
Finite-Time Analysis of Temporal Difference Learning: Discrete-Time Linear System Perspective
TD-learning is a fundamental algorithm in the field of reinforcement learning (RL), that is employed to evaluate a given policy by estimating the corresponding value function for a Markov decision process. While signific…
Reinforcement Learning (RL)Finite-time Safety and Reach-avoid Verification of Stochastic Discrete-time Systems
This paper studies finite-time safety and reach-avoid verification for stochastic discrete-time dynamical systems. The aim is to ascertain lower and upper bounds of the probability that, within a predefined finite-time h…
Time-adaptive high-order compact finite difference schemes for option pricing in a family of stochastic volatility models
We propose a time-adaptive, high-order compact finite difference scheme for option pricing in a family of stochastic volatility models. We employ a semi-discrete high-order compact finite difference method for the spatia…