research
∙
09/11/2023
Graph Matching in Correlated Stochastic Block Models for Improved Graph Clustering
We consider community detection from multiple correlated graphs sharing ...
share
research
∙
05/31/2023
Efficient Algorithms for Exact Graph Matching on Correlated Stochastic Block Models with Constant Correlation
We consider the problem of graph matching, or learning vertex correspond...
research
∙
01/12/2023
Detection problems in the spiked matrix models
We study the statistical decision process of detecting the low-rank sign...
research
∙
01/03/2023
Data Valuation Without Training of a Model
Many recent works on understanding deep learning try to quantify how muc...
research
∙
12/29/2022
Recovering Top-Two Answers and Confusion Probability in Multi-Choice Crowdsourcing
Crowdsourcing has emerged as an effective platform to label a large volu...
research
∙
12/19/2022
Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization
The nonconvex formulation of matrix completion problem has received sign...
research
∙
03/02/2022
Asymptotic Normality of Log Likelihood Ratio and Fundamental Limit of the Weak Detection for Spiked Wigner Matrices
We consider the problem of detecting the presence of a signal in a rank-...
research
∙
11/19/2021
A Worker-Task Specialization Model for Crowdsourcing: Efficient Inference and Fundamental Limits
Crowdsourcing system has emerged as an effective platform to label data ...
research
∙
04/28/2021
Detection of Signal in the Spiked Rectangular Models
We consider the problem of detecting signals in the rank-one signal-plus...
research
∙
02/24/2021
Self-Diagnosing GAN: Diagnosing Underrepresented Samples in Generative Adversarial Networks
Despite remarkable performance in producing realistic samples, Generativ...
research
∙
03/23/2020
Hypergraph Clustering in the Weighted Stochastic Block Model via Convex Relaxation of Truncated MLE
We study hypergraph clustering under the weighted d-uniform hypergraph s...
research
∙
03/21/2020
Crowdsourced Labeling for Worker-Task Specialization Block Model
We consider crowdsourced labeling under a worker-task specialization blo...
research
∙
01/31/2020
Crowdsourced Classification with XOR Queries: Fundamental Limits and An Efficient Algorithm
Crowdsourcing systems have emerged as an effective platform to label dat...
research
∙
01/16/2020
Weak Detection in the Spiked Wigner Model with General Rank
We study the statistical decision process of detecting the presence of s...
research
∙
04/19/2019
Shallow Neural Network can Perfectly Classify an Object following Separable Probability Distribution
Guiding the design of neural networks is of great importance to save eno...
research
∙
09/28/2018
Weak detection of signal in the spiked Wigner model
We consider the problem of detecting the presence of the signal in a ran...
research
∙
09/04/2018
Parity Crowdsourcing for Cooperative Labeling
Consider a database of k objects, e.g., a set of videos, where each obje...
research
∙
12/01/2017