3 papers
cs.LG2026
PC Layer: Polynomial Weight Preconditioning for Improving LLM Pre-Training
Senmiao Wang, Tiantian Fang, Haoran Zhang +4
We propose a preconditioning (PC) layer, a weight parameterization via polynomial preconditioner that ensures stable weight conditioning throughout LLM training. The PC module resh…
stat.ML2025
Transformed Regularizations for Robust Principal Component Analysis: Toward a Fine-Grained Understanding
Kun Zhao, Haoke Zhang, Jiayi Wang +1
Robust Principal Component Analysis (RPCA) aims to recover a low-rank structure from noisy, partially observed data that is also corrupted by sparse, potentially large-magnitude ou…
math.ST2025
Noisy Low-Rank Matrix Completion via Transformed Regularization and its Theoretical Properties
Kun Zhao, Jiayi Wang, Yifei Lou
This paper focuses on recovering an underlying matrix from its noisy partial entries, a problem commonly known as matrix completion. We delve into the investigation of a non-convex…