Co-occurring keywords · papers mentioning both
Papers
Customizing the Inductive Biases of Softmax Attention using Structured Matrices
ICML 2025
ProcrustesGPT: Compressing LLMs with Structured Matrices and Orthogonal Transformations
ACL 2025
Compute Better Spent: Replacing Dense Layers with Structured Matrices
ICML 2024
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
NeurIPS 2024
Structured adaptive and random spinners for fast machine learning computations
AISTATS 2017
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
ICML 2017
Orthogonal Random Features
NeurIPS 2016