519 citations · 741 across the 13 of their papers we have counts for
6 papers · 1 filter
Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations
Anudhyan Boral, Zhong Yi Wan, Leonardo Zepeda-Núñez +5
We introduce a data-driven learning framework that assimilates two powerful ideas: ideal large eddy simulation (LES) from turbulence closure modeling and neural stochastic differen…
Policy-Induced Self-Supervision Improves Representation Finetuning in Visual RL
Sébastien M. R. Arnold, Fei Sha
We study how to transfer representations pretrained on source tasks to target tasks in visual percept based RL. We analyze two popular approaches: freezing or finetuning the pretra…
Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems
Zhong Yi Wan, Leonardo Zepeda-Núñez, Anudhyan Boral +1
We present a data-driven, space-time continuous framework to learn surrogate models for complex physical systems described by advection-dominated partial differential equations. Th…
Two-Stage Metric Learning
Jun Wang, Ke Sun, Fei Sha +2
In this paper, we present a novel two-stage metric learning algorithm. We first map each learning instance to a probability distribution by computing its similarities to a set of f…
Information-Theoretical Learning of Discriminative Clusters for Unsupervised Domain Adaptation
Yuan Shi, Fei Sha
We study the problem of unsupervised domain adaptation, which aims to adapt classifiers trained on a labeled source domain to an unlabeled target domain. Many existing approaches f…
Marginalized Denoising Autoencoders for Domain Adaptation
Minmin Chen, Zhixiang Xu, Kilian Weinberger +1
Stacked denoising autoencoders (SDAs) have been successfully used to learn new representations for domain adaptation. Recently, they have attained record accuracy on standard bench…