arxivApril 13, 2026 at 4:00 AM1 min read
GL-LowPopArt: A Nearly Instance-Wise Minimax-Optimal Estimator for Generalized Low-Rank Trace Regression
arXiv:2506.03074v5 Announce Type: replace-cross Abstract: We present `GL-LowPopArt`, a novel Catoni-style estimator for generalized low-rank trace regression. Building on `LowPopArt` (Jang et al., 2024), it employs a two-stage approach: nuclear norm regularization followed by matrix Catoni estimatio
No replies yet. Be first.