31 citations · 40 across the 30 of their papers we have counts for
8 papers · 1 filter
Model-free learning of probability flows: Elucidating the nonequilibrium dynamics of flocking
Nicholas M. Boffi, Eric Vanden-Eijnden
Active systems comprise a class of nonequilibrium dynamics in which individual components autonomously dissipate energy. Efforts towards understanding the role played by activity h…
An Efficient On-Policy Deep Learning Framework for Stochastic Optimal Control
Mengjian Hua, Mathieu Laurière, Eric Vanden-Eijnden
We present a novel on-policy algorithm for solving stochastic optimal control (SOC) problems. By leveraging the Girsanov theorem, our method directly computes on-policy gradients o…
NETS: A Non-Equilibrium Transport Sampler
Michael S. Albergo, Eric Vanden-Eijnden
We propose an algorithm, termed the Non-Equilibrium Transport Sampler (NETS), to sample from unnormalized probability distributions. NETS can be viewed as a variant of annealed imp…
Flow map matching with stochastic interpolants: A mathematical framework for consistency models
Nicholas M. Boffi, Michael S. Albergo, Eric Vanden-Eijnden
Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inf…
Evolving motility of active droplets is captured by a self-repelling random walk model
Wenjun Chen, Adrien Izzet, Ruben Zakine +3
Swimming droplets are a class of active particles whose motility changes as a function of time due to shrinkage and self-avoidance of their trail. Here we combine experiments and t…
Sequential-in-time training of nonlinear parametrizations for solving time-dependent partial differential equations
Huan Zhang, Yifan Chen, Eric Vanden-Eijnden +1
Sequential-in-time methods solve a sequence of training problems to fit nonlinear parametrizations such as neural networks to approximate solution trajectories of partial different…
Probabilistic Forecasting with Stochastic Interpolants and Föllmer Processes
Yifan Chen, Mark Goldstein, Mengjian Hua +3
We propose a framework for probabilistic forecasting of dynamical systems based on generative modeling. Given observations of the system state over time, we formulate the forecasti…
SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers
Nanye Ma, Mark Goldstein, Michael S. Albergo +3
We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which allows for…