activity
20162026
most citedFourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

455 citations · 1.5k across the 69 of their papers we have counts for

collaborators
Showing 2022 · cs.LGShow all

9 papers · 2 filters

cs.LG2022★ 17 cited

Fast Sampling of Diffusion Models via Operator Learning

Hongkai Zheng, Weili Nie, Arash Vahdat +2

Diffusion models have found widespread adoption in various areas. However, their sampling process is slow because it requires hundreds to thousands of network evaluations to emulat…

cs.LG2022★ 158 cited

Real-time high-resolution CO geological storage prediction using nested Fourier neural operators

Gege Wen, Zongyi Li, Qirui Long +3

Carbon capture and storage (CCS) plays an essential role in global decarbonization. Scaling up CCS deployment requires accurate and high-resolution modeling of the storage reservoi…

cs.LG2022

Off-Policy Risk Assessment in Markov Decision Processes

Audrey Huang, Liu Leqi, Zachary Chase Lipton +1

Addressing such diverse ends as safety alignment with human preferences, and the efficiency of learning, a growing line of reinforcement learning research focuses on risk functiona…

cs.LG2022★ 4 cited

Langevin Monte Carlo for Contextual Bandits

Pan Xu, Hongkai Zheng, Eric Mazumdar +2

We study the efficiency of Thompson sampling for contextual bandits. Existing Thompson sampling-based algorithms need to construct a Laplace approximation (i.e., a Gaussian distrib…

cs.LG2022★ 1 cited

Thompson Sampling Achieves Regret in Linear Quadratic Control

Taylan Kargin, Sahin Lale, Kamyar Azizzadenesheli +2

Thompson Sampling (TS) is an efficient method for decision-making under uncertainty, where an action is sampled from a carefully prescribed distribution which is updated based on t…

cs.LG2022★ 4 cited

KCRL: Krasovskii-Constrained Reinforcement Learning with Guaranteed Stability in Nonlinear Dynamical Systems

Sahin Lale, Yuanyuan Shi, Guannan Qu +3

Learning a dynamical system requires stabilizing the unknown dynamics to avoid state blow-ups. However, current reinforcement learning (RL) methods lack stabilization guarantees, w…