Dong Huang · Research
Research
My research interests are in statistics, probability and theoretical computer science.
α–β denotes alphabetical author order. (*) denotes equal contribution.
Manuscripts
6-
-
Graph Matching in Random Geometric Graphs I: Efficient Algorithms
-
Detecting Random Geometric Graphs with General Kernel
-
Fundamental Limits of Community Detection in Contextual Multi-Layer Stochastic Block Models
Submitted
-
Sample Complexity of Correlation Detection in Erdős-Rényi Graphs
Submitted
Awarded 2026 IMS Hannan Graduate Student Travel Award.
-
Testing Correlation in Graphs by Counting Bounded Degree Motifs
Submitted
Publications
6-
Learning Global Temporal Dynamics in Sparse Networks via Cycle Counts
The 40th Annual Conference on Neural Information Processing Systems (NeurIPS), 2026
-
Prompt Perturbation for Reliable LLM Evaluation over Comparison Graphs
Statistical Learning and Data Science (SLADS), to appear
Outstanding Poster Award at the 10th Tsinghua-Peking Statistics Forum.
-
Attributed Network Alignment: Statistical Limits and Efficient Algorithm
The 43rd International Conference on Machine Learning (ICML), 2026
-
Sample Complexity of Correlation Detection in the Gaussian Wigner Model
The 42nd International Conference on Machine Learning (ICML), 2025
-
Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
IEEE Transactions on Information Theory, 2025 (long version)
The 37th Conference on Learning Theory (COLT), 2024 (short version) -
Graph Over-Parameterization: Why the Graph Helps the Training of Deep Graph Convolutional Network
Neurocomputing, 2023