6 papers
Provable Benefit of Sign Descent: A Minimal Model Under Heavy-Tailed Class Imbalance
Robin Yadav, Shuo Xie, Tianhao Wang +1
Adaptive optimization methods (such as Adam) play a major role in LLM pretraining, significantly outperforming Gradient Descent (GD). Recent studies have proposed new smoothness as…
A Tale of Two Geometries: Adaptive Optimizers and Non-Euclidean Descent
Shuo Xie, Tianhao Wang, Beining Wu +1
Adaptive optimizers can reduce to normalized steepest descent (NSD) when only adapting to the current gradient, suggesting a close connection between the two algorithmic families.…
Structured Preconditioners in Adaptive Optimization: A Unified Analysis
Shuo Xie, Tianhao Wang, Sashank Reddi +2
We present a novel unified analysis for a broad class of adaptive optimization algorithms with structured (e.g., layerwise, diagonal, and kronecker-factored) preconditioners for bo…
Adam Exploits -geometry of Loss Landscape via Coordinate-wise Adaptivity
Shuo Xie, Mohamad Amin Mohamadi, Zhiyuan Li
Adam outperforms SGD when training language models. Yet this advantage is not well-understood theoretically -- previous convergence analysis for Adam and SGD mainly focuses on the…
Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
Han Shao, Shuo Xie, Kunhe Yang
Strategic classification addresses a learning problem where a decision-maker implements a classifier over agents who may manipulate their features in order to receive favorable pre…
MPPO: Multi Pair-wise Preference Optimization for LLMs with Arbitrary Negative Samples
Shuo Xie, Fangzhi Zhu, Jiahui Wang +6
Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Re…