Search Results for author:
Found 8 papers, 2 papers with code
Cross Entropy versus Label Smoothing: A Neural Collapse Perspective
We first show empirically that models trained with label smoothing converge faster to neural collapse solutions and attain a stronger level of neural collapse.
Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data
In this paper, we study the extension of N C phenomenon to the imbalanced data under cross-entropy loss function in the context of unconstrained feature model.
Improved theoretical guarantee for rank aggregation via spectral method
As it is generally NP-hard to find a global ranking that minimizes the mismatch (known as the Kemeny optimization), we focus on the Erd\"os-R\'enyi outliers (ERO) model for this ranking problem.
Generalized Orthogonal Procrustes Problem under Arbitrary Adversaries
We study the semidefinite relaxation (SDR) and an iterative method named generalized power method (GPM) to find the least squares estimator, and investigate the performance under a signal-plus-noise model.
Near-Optimal Performance Bounds for Orthogonal and Permutation Group Synchronization via Spectral Methods
In particular, for orthogonal group synchronization, we obtain a near-optimal performance bound for the group recovery in presence of additive Gaussian noise.
Strong Consistency, Graph Laplacians, and the Stochastic Block Model
We study the performance of classical two-step spectral clustering via the graph Laplacian to learn the stochastic block model.
Certifying Global Optimality of Graph Cuts via Semidefinite Relaxation: A Performance Guarantee for Spectral Clustering
This paper is devoted to the theoretical foundations of spectral clustering and graph cuts.
Rapid, Robust, and Reliable Blind Deconvolution via Nonconvex Optimization
To the best of our knowledge, our algorithm is the first blind deconvolution algorithm that is numerically efficient, robust against noise, and comes with rigorous recovery guarantees under certain subspace conditions.
Information Theory Information Theory
