8 papers
BLISS: A Lightweight Bilevel Influence Scoring Method for Data Selection in Language Model Pretraining
Jie Hao, Rui Yu, Wei Zhang +3
Effective data selection is essential for pretraining large language models (LLMs), enhancing efficiency and improving generalization to downstream tasks. However, existing approac…
Bilevel Optimization with Lower-Level Uniform Convexity: Theory and Algorithm
Yuman Wu, Xiaochuan Gong, Jie Hao +1
Bilevel optimization is a hierarchical framework where an upper-level optimization problem is constrained by a lower-level problem, commonly used in machine learning applications s…
Noise-Adaptive Layerwise Learning Rates: Accelerating Geometry-Aware Optimization for Deep Neural Network Training
Jie Hao, Xiaochuan Gong, Jie Xu +2
Geometry-aware optimization algorithms, such as Muon, have achieved remarkable success in training deep neural networks (DNNs). These methods leverage the underlying geometry of DN…
Adaptive Algorithms with Sharp Convergence Rates for Stochastic Hierarchical Optimization
Xiaochuan Gong, Jie Hao, Mingrui Liu
Hierarchical optimization refers to problems with interdependent decision variables and objectives, such as minimax and bilevel formulations. While various algorithms have been pro…
Personalized Federated Fine-tuning for Heterogeneous Data: An Automatic Rank Learning Approach via Two-Level LoRA
Jie Hao, Yuman Wu, Ali Payani +2
We study the task of personalized federated fine-tuning with heterogeneous data in the context of language models, where clients collaboratively fine-tune a language model (e.g., B…
On the Convergence of Adam-Type Algorithm for Bilevel Optimization under Unbounded Smoothness
Xiaochuan Gong, Jie Hao, Mingrui Liu
Adam has become one of the most popular optimizers for training modern deep neural networks, such as transformers. However, its applicability is largely restricted to single-level…