Skip to content
conftrace_

feature matrix

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

post-hoc detection (1) large language model (1) feature removal (1) rank-1 matrix (1) dictionary extraction (1) feedback (1) sparse superposed features (1) rank-one component (1) spectrum (1) spike (1)

Papers

The Complexity of Learning Sparse Superposed Features with Feedback ICML 2025 A Theory of Non-Linear Feature Learning with One Gradient Step in Two-Layer Neural Networks ICML 2024 RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection NeurIPS 2022 Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations ICML 2017