Skip to content
conftrace_

outlier feature

2 papers

Explore in graph

Also known as

OF

Co-occurring keywords · papers mentioning both

activation normalization (1) l1-norm minimization (1) preconditioning optimizer (1) min-max optimization (1) transformer training (1) distance metric learning (1) neural network optimization (1) model quantization (1) transformer architecture (1) model compression (1)

Papers

Understanding and Minimising Outlier Features in Transformer Training NeurIPS 2024 Robust Distance Metric Learning via Simultaneous L1-Norm Minimization and Maximization ICML 2014