[HTML][HTML] Data-distribution-informed Nyström approximation for structured data using vector quantization-based landmark determination
We present an effective method for supervised landmark selection in sparse Nyström
approximations of kernel matrices for structured data. Our approach transforms structured …
approximations of kernel matrices for structured data. Our approach transforms structured …
Elliptical Attention
SK Nielsen, LU Abdullaev, R Teo… - arXiv preprint arXiv …, 2024 - arxiv.org
Pairwise dot-product self-attention is key to the success of transformers that achieve state-of-
the-art performance across a variety of applications in language and vision. This dot-product …
the-art performance across a variety of applications in language and vision. This dot-product …
Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes
While the great capability of Transformers significantly boosts prediction accuracy, it could
also yield overconfident predictions and require calibrated uncertainty estimation, which can …
also yield overconfident predictions and require calibrated uncertainty estimation, which can …
An SVD-like Decomposition of Bounded-Input Bounded-Output Functions
The Singular Value Decomposition (SVD) of linear functions facilitates the calculation of
their 2-induced norm and row and null spaces, hallmarks of linear control theory. In this …
their 2-induced norm and row and null spaces, hallmarks of linear control theory. In this …
Fairness-Aware Attention for Contrastive Learning
S Nielsen, TM Nguyen - openreview.net
Contrastive learning has proven instrumental in learning unbiased representations of data,
especially in complex environments characterized by high-cardinality and high-dimensional …
especially in complex environments characterized by high-cardinality and high-dimensional …