Stein's method compares probability distributions through the study of a class of linear
operators called Stein operators. While mainly studied in probability and used to underpin …

Score distillation sampling (SDS) has shown great promise in text-to-3D generation by
distilling pretrained large-scale text-to-image diffusion models, but suffers from over …

In this survey, we describe controlled interacting particle systems (CIPS) to approximate the
solution of the optimal filtering and the optimal control problems. Part I of the survey is …

Deep ensembles have recently gained popularity in the deep learning community for their
conceptual simplicity and efficiency. However, maintaining functional diversity between …

Recent work on adversarial attack has shown that Projected Gradient Descent (PGD)
Adversary is a universal first-order adversary, and the classifier adversarially trained by PGD …

Bayesian inference problems require sampling or approximating high-dimensional
probability distributions. The focus of this paper is on the recently introduced Stein …

Sequence-to-sequence models are commonly trained via maximum likelihood estimation
(MLE). However, standard MLE training considers a word-level objective, predicting the next …

Particle-based variational inference methods (ParVIs) have gained attention in the Bayesian
inference literature, for their capacity to yield flexible and accurate approximations. We …

MC Dropout is a mainstream" free lunch" method in medical imaging for approximate
Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC …

While Bayesian neural networks (BNNs) have drawn increasing attention, their posterior
inference remains challenging, due to the high-dimensional and over-parameterized nature …