8 papers
Prompt Perturbation for Reliable LLM Evaluation over Comparison Graphs
Dong Huang, Jianbo Sun, Pengkun Yang
Evaluating large language models (LLMs) is important for understanding their capabilities, comparing competing systems, and supporting the deployment of reliable models in practice…
Testing Correlation in Graphs by Counting Bounded Degree Motifs
Dong Huang, Pengkun Yang
We investigate the problem of detecting correlation between two ErdÅs-Rényi graphs , formulated as a hypothesis testing problem: under the null hypothesis, the two graphs…
Minimax estimation of functionals in sparse vector model with correlated observations
Yuhao Wang, Pengkun Yang, Alexandre B. Tsybakov
We consider the observations of an unknown -sparse vector corrupted by Gaussian noise with zero mean and unknown covariance matrix . We propos…
Information-Theoretic and Computational Limits of Correlation Detection under Graph Sampling
Dong Huang, Pengkun Yang
Correlation analysis is a fundamental problem in statistics. In this paper, we consider the correlation detection problem between a pair of Erdos-Renyi graphs. Specifically, the pr…
Nonparametric Inference on Unlabeled Histograms
Yun Ma, Pengkun Yang
Statistical inference on histograms and frequency counts plays a central role in categorical data analysis. Moving beyond classical methods that directly analyze labeled frequencie…
Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
Dong Huang, Xianwen Song, Pengkun Yang
This paper studies the problem of recovering the hidden vertex correspondence between two correlated random graphs. We propose the partially correlated ErdÅs-Rényi graphs model,…