1.1k citations · 2.4k across the 69 of their papers we have counts for
7 papers · 1 filter
Enhancing the Locality and Breaking the Memory Bottleneck of Transformer on Time Series Forecasting
Shiyang Li, Xiaoyong Jin, Yao Xuan +4
Time series forecasting is an important problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation. In this…
Doubly Robust Crowdsourcing
Chong Liu, Yu-Xiang Wang
Large-scale labeled dataset is the indispensable fuel that ignites the AI revolution as we see today. Most such datasets are constructed using crowdsourcing services such as Amazon…
Towards Optimal Off-Policy Evaluation for Reinforcement Learning with Marginalized Importance Sampling
Tengyang Xie, Yifei Ma, Yu-Xiang Wang
Motivated by the many real-world applications of reinforcement learning (RL) that require safe-policy iterations, we consider the problem of off-policy evaluation (OPE) -- the prob…
Online Forecasting of Total-Variation-bounded Sequences
Dheeraj Baby, Yu-Xiang Wang
We consider the problem of online forecasting of sequences of length with total-variation at most using observations contaminated by independent -subgaussian noise. We…
Provably Efficient Q-Learning with Low Switching Cost
Yu Bai, Tengyang Xie, Nan Jiang +1
We take initial steps in studying PAC-MDP algorithms with limited adaptivity, that is, algorithms that change its exploration policy as infrequently as possible during regret minim…
A Higher-Order Kolmogorov-Smirnov Test
Veeranjaneyulu Sadhanala, Yu-Xiang Wang, Aaditya Ramdas +1
We present an extension of the Kolmogorov-Smirnov (KS) two-sample test, which can be more sensitive to differences in the tails. Our test statistic is an integral probability metri…
Imitation-Regularized Offline Learning
Yifei Ma, Yu-Xiang Wang, Balakrishnan +1
We study the problem of offline learning in automated decision systems under the contextual bandits model. We are given logged historical data consisting of contexts, (randomized)…