Variational Schr\" odinger Diffusion Models

W Deng, W Luo, Y Tan, M Biloš, Y Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Schr\" odinger bridge (SB) has emerged as the go-to method for optimizing transportation
plans in diffusion models. However, SB requires estimating the intractable forward score …

Neural Shr\" odinger Bridge Matching for Pansharpening

Z Cao, X Wu, LJ Deng - arXiv preprint arXiv:2404.11416, 2024 - arxiv.org
Recent diffusion probabilistic models (DPM) in the field of pansharpening have been
gradually gaining attention and have achieved state-of-the-art (SOTA) performance. In this …

Recurrent Interpolants for Probabilistic Time Series Prediction

Y Chen, M Biloš, S Mittal, W Deng, K Rasul… - arXiv preprint arXiv …, 2024 - arxiv.org
Sequential models like recurrent neural networks and transformers have become standard
for probabilistic multivariate time series forecasting across various domains. Despite their …

Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics

H Zheng, H Du, Q Feng, W Deng, G Lin - arXiv preprint arXiv:2405.07839, 2024 - arxiv.org
Replica exchange stochastic gradient Langevin dynamics (reSGLD) is an effective sampler
for non-convex learning in large-scale datasets. However, the simulation may encounter …

Schr\"{o} dinger Bridge with Quadratic State Cost is Exactly Solvable

AMH Teter, W Wang, A Halder - arXiv preprint arXiv:2406.00503, 2024 - arxiv.org
Schr\" odinger bridge is a diffusion process that steers a given distribution to another in a
prescribed time while minimizing the effort to do so. It can be seen as the stochastic …