works on

From the 1 of 12 linked papers with an AI index.

collaborators

12 papers

math.PR2026

Sharp small-deviation inequalities for sums of independent nonnegative random variables

Weibo Fu, Yanjun Han, Guanyang Wang +3

Let be independent nonnegative random variables with , and write . For , we prove that \[ \mathbb{P}\left(S<\mathbb{E} S+Î…

math.PR2026

Spectral Gap for the Binary Fixed-Margin Swap Chain

Weibo Fu, Qian Qin, Guanyang Wang

The paper establishes an explicit lower bound on the spectral gap of the lazy swap chain used to sample binary matrices with given row and column sums, thereby proving the Kannan‑T…

cs.LG2026

Weak Diffusion Priors Can Still Achieve Strong Inverse-Problem Performance

Jing Jia, Wei Yuan, Sifan Liu +2

Can a diffusion model trained on bedrooms recover human faces? Diffusion models are widely used as priors for inverse problems, but standard approaches usually assume a high-fideli…

stat.CO2026

Markov chain Monte Carlo without evaluating the target: an auxiliary variable approach

Wei Yuan, Guanyang Wang

In sampling tasks, it is common for target distributions to be known up to a normalizing constant. However, in many situations, even evaluating the unnormalized distribution can be…

cs.LG2026

TabClustPFN: A Prior-Fitted Network for Tabular Data Clustering

Tianqi Zhao, Guanyang Wang, Yan Shuo Tan +1

Clustering tabular data is a fundamental yet challenging problem due to heterogeneous feature types, diverse data-generating mechanisms, and the absence of transferable inductive b…

cs.LG2026

Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse Solvers

Xiaoyu Qiu, Taewon Yang, Zhanhao Liu +2

Uncertainty evaluation is critical in scientific and engineering inverse problems. However, existing benchmarks on Diffusion Inverse Solvers (DIS) primarily focus on reconstruction…