arXiv:2607. 00586v2 Announce Type: replace-cross Abstract: We present a simple, yet general approach to study the scaling properties as the dimensionality of Metropolised MCMC sampling algorithms increases.
By P. Dobson, J. M. Sanz-Serna, K. C. Zygalakis
arXiv:2607. 23008v1 Announce Type: cross Abstract: Optimization over probability measures has become an increasingly important paradigm in modern machine learning, scientific computing, and uncertainty quantification.
By Jiaqi Tang, Qin Li, Wilfrid Gangbo
arXiv:2609.37227v1 Announce Type: new
Abstract: Inference-time steering adapts pretrained diffusion and flow-based models to new tasks, e.g., to generate samples from a conditional distribution or sa...
By Adhithyan Kalaivanan, Zheng Zhao, Jens Sj\"olund, Fredrik Lindsten
The paper introduces a new Markov chain Monte Carlo method that samples from multimodal distributions by interpolating along the diffusion path of a noising diffusion process, preserving mode weights and improving mixing. It proposes a Metropolis-adjusted diffusion path (MAD-Path) sampler that corrects for bias from approximate score estimates and discretization errors, ensuring the target distribution remains invariant. Experiments on Bayesian posteriors demonstrate that MAD-Path outperforms tempering-based MCMC and unadjusted diffusion samplers in global exploration and accurate mode-weight estimation.
By Han Chen, Sifan Liu, Jun Yang
arXiv:2512. 08022v2 Announce Type: replace-cross Abstract: We propose a novel diffusion-based posterior sampling method within a plug-and-play framework.
By Jinyuan Chang, Chenguang Duan, Yuling Jiao, Ruoxuan Li, Jerry Zhijian Yang, Cheng Yuan
The paper presents a new one‑step generative modeling framework for finite state spaces, leveraging discrete Wasserstein geometry to define a target‑relative KL gradient flow over a reversible Markov kernel. The authors implement this flow at the particle level using Markov jumps and encode the resulting transport updates into a latent‑conditioned generator, enabling one‑step inference after training. Experiments on a controlled setting confirm KL dissipation, consistency between particle dynamics and probability flow, and accurate numerical scaling, while a finite‑capacity neural generator successfully tracks the exact transport targets.
By Alessandro Micheli, Andrea Zerio, Samir Bhatt