Search Results for author:
Found 5 papers, 0 papers with code
Contrastive Learning with Orthonormal Anchors (CLOA)
This study focuses on addressing the instability issues prevalent in contrastive learning, specifically examining the InfoNCE loss function and its derivatives.
TransFusion: Contrastive Learning with Transformers
This paper proposes a novel framework, TransFusion, designed to make the process of contrastive learning more analytical and explainable.
Fusion Subspace Clustering for Incomplete Data
This paper introduces {\em fusion subspace clustering}, a novel method to learn low-dimensional structures that approximate large scale yet highly incomplete data.
Geometry of the Minimum Volume Confidence Sets
Prior work showed the minimum-volume confidence sets are the level-sets of a discontinuous function defined by an exact p-value.
Tensor Methods for Nonlinear Matrix Completion
This approach will succeed in many cases where traditional LRMC is guaranteed to fail because the data are low-rank in the tensorized representation but not in the original representation.
