conftrace_

sparse rate reduction

3 papers

Explore in graph

Also known as

SRR

Co-occurring keywords · papers mentioning both

transformer architecture (3) token compression (2) representation learning (2) white-box model (1) feature compression (1) compress and sparsify (1) generalization ability (1) neural network optimization (1) vision transformer (1) dimensionality reduction (1)

Papers

An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models NeurIPS 2024 White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is? JMLR 2024 White-Box Transformers via Sparse Rate Reduction NeurIPS 2023