collaborators

7 papers

math.OC2026

A lower bound for stepsize-based acceleration of gradient descent

Jianhao Ma, Yuxin Chen

Recent work has shown that, for smooth convex optimization, plain gradient descent can be accelerated from its textbook convergence rate of (where denotes the numbe…

cs.LG2026

WSqD: A Horizon-Free Learning Rate Schedule for Large Model Training

Jianhao Ma, Yuxin Chen

Standard learning rate schedules such as cosine annealing are tied to a fixed training horizon, limiting their ability to accommodate post hoc horizon extension. Warmup-stable-deca…

cs.LG2026

Towards Understanding the Power and Limits of the Muon Optimizer: A River-Valley Perspective

Tianqi Shen, Jinji Yang, Runze Shi +3

Recently, Muon has gained substantial attention as an appealing alternative to Adam-like optimizers, with many works highlighting its advantages through spectral normalization and…

cs.LG2026

Preconditioning Benefits of Spectral Orthogonalization in Muon

Jianhao Ma, Yu Huang, Yuejie Chi +1

The Muon optimizer, a matrix-structured algorithm that leverages spectral orthogonalization of gradients, is a milestone in the pretraining of large language models. However, the u…

cs.AI2026

LIBRA: Language Model Informed Bandit Recourse Algorithm for Personalized Treatment Planning

Junyu Cao, Ruijiang Gao, Esmaeil Keyvanshokooh +1

We introduce a unified framework that seamlessly integrates algorithmic recourse, contextual bandits, and large language models (LLMs) to support sequential decision-making in high…

cs.LG2025

Quantization through Piecewise-Affine Regularization: Optimization and Statistical Guarantees

Jianhao Ma, Lin Xiao

Optimization problems over discrete or quantized variables are very challenging in general due to the combinatorial nature of their search space. Piecewise-affine regularization (P…