5 papers · 1 filter
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…
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…
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…
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…
PARQ: Piecewise-Affine Regularized Quantization
Lisa Jin, Jianhao Ma, Zechun Liu +3
We develop a principled method for quantization-aware training (QAT) of large-scale machine learning models. Specifically, we show that convex, piecewise-affine regularization (PAR…