4 papers
Delocalization of bias in unadjusted Hamiltonian Monte Carlo and underdamped Langevin
Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed +1
Unadjusted samplers such as unadjusted Hamiltonian Monte Carlo and underdamped Langevin are well-known to be biased. Metropolis--Hastings adjustment has been conventionally incorpo…
Convergence of Unadjusted Langevin in High Dimensions: Delocalization of Bias
Yifan Chen, Xiaoou Cheng, Jonathan Niles-Weed +1
The unadjusted Langevin algorithm is commonly used to sample probability distributions in extremely high-dimensional settings. However, existing analyses of the algorithm for stron…
The surprising efficiency of temporal difference learning for rare event prediction
Xiaoou Cheng, Jonathan Weare
We quantify the efficiency of temporal difference (TD) learning over the direct, or Monte Carlo (MC), estimator for policy evaluation in reinforcement learning, with an emphasis on…
Improved Active Learning via Dependent Leverage Score Sampling
Atsushi Shimizu, Xiaoou Cheng, Christopher Musco +1
We show how to obtain improved active learning methods in the agnostic (adversarial noise) setting by combining marginal leverage score sampling with non-independent sampling strat…