collaborators

7 papers

cs.LG2026

Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks

Tianyu Pang, Vignesh Kothapalli, Shenyang Deng +3

We study optimal learning-rate selection in two-layer and three-layer linear neural networks trained to learn linear target functions. In particular, we derive the exact closed-for…

cs.LG2026

Depth, Not Data: An Analysis of Hessian Spectral Bifurcation

Shenyang Deng, Boyao Liao, Zhuoli Ouyang +2

The eigenvalue distribution of the Hessian matrix plays a crucial role in understanding the optimization landscape of deep neural networks. Prior work has attributed the well-docum…

cs.LG2026

HTMuon: Improving Muon via Heavy-Tailed Spectral Correction

Tianyu Pang, Yujie Fang, Zihang Liu +4

Muon has recently shown promising results in LLM training. In this work, we study how to further improve Muon. We argue that Muon's orthogonalized update rule suppresses the emerge…

cs.LG2026

RMNP: Row-Momentum Normalized Preconditioning for Scalable Matrix-Based Optimization

Shenyang Deng, Zhuoli Ouyang, Tianyu Pang +4

Preconditioned adaptive methods have gained significant attention for training deep neural networks, as they capture rich curvature information of the loss landscape. The central c…

cs.LG2026

Suspicious Alignment of SGD: A Fine-Grained Step Size Condition Analysis

Shenyang Deng, Boyao Liao, Zhuoli Ouyang +3

This paper explores the suspicious alignment phenomenon in stochastic gradient descent (SGD) under ill-conditioned optimization, where the Hessian spectrum splits into dominant and…

cs.LG2025

From Spikes to Heavy Tails: Unveiling the Spectral Evolution of Neural Networks

Vignesh Kothapalli, Tianyu Pang, Shenyang Deng +2

Training strategies for modern deep neural networks (NNs) tend to induce a heavy-tailed (HT) empirical spectral density (ESD) in the layer weights. While previous efforts have show…