214 citations · 262 across the 32 of their papers we have counts for
9 papers · 1 filter
Architecture Alignment With Sparse Priors in Tabular Foundation Models
Tianqi Zhao, Tianyi Zhuang, Shuo Duan +3
Tabular foundation models (TFMs) are increasingly popular because they deliver strong predictions on new datasets through in-context learning, without task-specific training or ext…
The Snake Algorithm: A Rejection-Free Sampler for Binary Matrices with Fixed Margins
Zipei Nie, Guanyang Wang, Peng Zhang
We study uniform sampling of binary matrices with fixed row and column sums, a recurring problem in ecological null models, Rasch-model testing, network analysis, and combinatorics…
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+δ\…
Spectral Gap for the Binary Fixed-Margin Swap Chain
Weibo Fu, Qian Qin, Guanyang Wang
We prove an explicit spectral-gap lower bound for the lazy swap chain on binary matrices with prescribed row and column sums. This chain is a standard sampler for fixed-margin null…
Couple to Control: Joint Initial Noise Design in Diffusion Models
Jing Jia, Liyue Shen, Guanyang Wang
Diffusion models typically generate image batches from independent Gaussian initial noises. We argue that this independence assumption is only one choice within a broader class of…
Optimal Quantum Speedups for Repeatedly Nested Expectation Estimation
Yihang Sun, Guanyang Wang, Jose Blanchet
We study the estimation of repeatedly nested expectations (RNEs) with a constant horizon (number of nestings) using quantum computing. We propose a quantum algorithm that achieves…
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…
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…
TabClustPFN: A Prior-data Fitted Network for Tabular Data Clustering
Tianqi Zhao, Guanyang Wang, Yan Shuo Tan +1
Prior-data Fitted Networks (PFNs) have reframed supervised tabular learning as single-pass in-context inference without per-dataset optimization. Extending this paradigm to cluster…