8 papers
Sampling with collective variables: Relative error analysis for umbrella sampling under general conditions
Holden Lee, Matheau Santana-Gijzen, Jonathan Weare
We consider the problem of estimating the expectation of a function (observable) with respect to a high-dimensional probability distribution, under the assumption that a low-dimens…
Dimension-independent eigenvalue approximation for sparse matrices
Natalia Hajlasz, Christopher Musco, Jonathan Weare +1
Many applications in science and engineering require solving sparse Hermitian eigenvalue problems that are so large that even algorithms whose runtime scales linearly with the matr…
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…
Composing diffusion priors with explicit physical context via generative Gibbs sampling
Weizhou Wang, Jonathan Weare, Aaron R. Dinner
Pretrained diffusion models provide powerful learned priors, but in scientific sampling the target distribution often depends on physical context that is not fully represented by o…
Functional Estimation of the Marginal Likelihood
Omiros Papaspiliopoulos, Timothée Stumpf-Fétizon, Jonathan Weare
We propose a framework for computing, optimizing and integrating with respect to a smooth marginal likelihood in statistical models that involve high-dimensional parameters/latent…
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…