20 results for “ODE-based Iterative Sampling”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
The paper introduces Strong Stochastic Flow Maps (SSFMs), a novel framework that directly learns the strong solution map of additive-noise Stochastic Differential Equations (SDEs), enabling few-step s…
The paper studies sampling and recovery for tensor-valued dynamical systems using partial spatial observations over time.
Cole Becker, Taylan Kargin, Kimia Hassibi, Asuman Ozdaglar +1 more
This paper introduces a new framework for joint schedule/discretization design in generative modeling based on analyticity properties of ODE trajectories.
Zhengkai Pan, Peter Potaptchik, Wenxi Yao, Michael S. Albergo +1 more
The paper introduces the Itô map, a one-step stochastic flow map for predicting future states from intermediate states and Brownian paths.
A framework is proposed to identify governing PDEs from observational data by constructing finite-dimensional Koopman operators using Chebyshev spectral representations and enabling comparison between…
The paper introduces Flow Annealing Posterior Sampling (FAPS), a function-space posterior sampling framework for stochastic-process regression and PDE inverse problems.
The paper develops a quantitative framework to analyze and improve flow distillation in diffusion models, providing stability guarantees and suggesting non-uniform time scheduling to reduce approximat…
This paper determines that verifying global parameter identifiability for linear ODE models is an NP-hard problem, establishing a computational complexity boundary for the field.
The paper introduces a framework for sequentially approximating functions of elements in a slowly-varying sequence, improving upon previous work with a novel algorithm that scales the estimation budge…
Michael Y. Li, Anthony Zhan, Kanishk Gandhi, Noah D. Goodman +1 more
This paper introduces QuasiMoTTo, a method for generating correlated but exact samples in parallel to improve sample efficiency in scaling inference compute and reinforcement learning.
Introduce Deep Second-Order Stochastic Residual Method (D2SRM) for high-dimensional, Hessian-dependent fully nonlinear parabolic PDEs, establish well-posedness, and develop population-level convergenc…
Daniel Waxman, Dmitry Batenkov, John Feser, Andy Zane +3 more
A probabilistic programming library, dynestyx, is introduced for Bayesian treatment of dynamical systems.
This paper introduces a variance-weighted batch distribution to improve the diversity of samples in diffusion models.
This paper proposes a method to improve few-step generation in diffusion models by introducing a marginal-alignment regularizer.
Yuanjian Xu, Jianing Hao, Wanbo Zhang, Zhong Li +1 more
The paper proposes DiReCT, a novel framework that treats data selection during LLM annealing as a constrained optimization problem based on the spectral geometry of the loss landscape, achieving state…
This paper presents a self-balancing sampler for sequential sampling that achieves faster convergence to a desired target law while maintaining unpredictability.
This paper proposes a randomized iterative method called Sequential Preconditioned Conjugate Gradient Method (SPCG) for large-scale linear statistical models, which significantly reduces computational…
This paper introduces a novel method to improve the performance of finite-dimensional diffusion policies by lifting them to a Cameron-Martin space and using a backward Kolmogorov equation.