Picture for Shuyang Ling

Shuyang Ling

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data

Add code
Sep 03, 2024
Viaarxiv icon

Cross Entropy versus Label Smoothing: A Neural Collapse Perspective

Add code
Feb 07, 2024
Viaarxiv icon

Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data

Add code
Sep 18, 2023
Viaarxiv icon

Improved theoretical guarantee for rank aggregation via spectral method

Add code
Sep 10, 2023
Viaarxiv icon

Generalized Power Method for Generalized Orthogonal Procrustes Problem: Global Convergence and Optimization Landscape Analysis

Add code
Jun 29, 2021
Figure 1 for Generalized Power Method for Generalized Orthogonal Procrustes Problem: Global Convergence and Optimization Landscape Analysis
Figure 2 for Generalized Power Method for Generalized Orthogonal Procrustes Problem: Global Convergence and Optimization Landscape Analysis
Viaarxiv icon

Near-Optimal Performance Bounds for Orthogonal and Permutation Group Synchronization via Spectral Methods

Add code
Aug 21, 2020
Figure 1 for Near-Optimal Performance Bounds for Orthogonal and Permutation Group Synchronization via Spectral Methods
Figure 2 for Near-Optimal Performance Bounds for Orthogonal and Permutation Group Synchronization via Spectral Methods
Figure 3 for Near-Optimal Performance Bounds for Orthogonal and Permutation Group Synchronization via Spectral Methods
Viaarxiv icon

Strong Consistency, Graph Laplacians, and the Stochastic Block Model

Add code
Apr 21, 2020
Figure 1 for Strong Consistency, Graph Laplacians, and the Stochastic Block Model
Figure 2 for Strong Consistency, Graph Laplacians, and the Stochastic Block Model
Figure 3 for Strong Consistency, Graph Laplacians, and the Stochastic Block Model
Figure 4 for Strong Consistency, Graph Laplacians, and the Stochastic Block Model
Viaarxiv icon

Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering

Add code
Jul 08, 2018
Figure 1 for Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering
Figure 2 for Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering
Figure 3 for Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering
Figure 4 for Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering
Viaarxiv icon