activity
20242026
collaborators

6 papers

cs.LG2026

Algorithmic Separation between Constant-Depth and Logarithmic-Depth Neural Networks

Yunwei Ren, Zihao Wang, Jason D. Lee

Despite the empirical advantages of deep networks over shallow ones, theoretical depth separations largely concern approximation power, while algorithmic results are mostly limited…

cs.AI2026

The Power of Power Law: Asymmetry Enables Compositional Reasoning

Zixuan Wang, Xingyu Dang, Jason D. Lee +1

Natural language data follows a power-law distribution, with most knowledge and skills appearing at very low frequency. While a common intuition suggests that reweighting or curati…

cs.LG2026

What Makes a Reward Model a Good Teacher? An Optimization Perspective

Noam Razin, Zixuan Wang, Hubert Strauss +3

The success of Reinforcement Learning from Human Feedback (RLHF) critically depends on the quality of the reward model. However, while this quality is primarily evaluated through a…

cs.LG2025

Learning Orthogonal Multi-Index Models: A Fine-Grained Information Exponent Analysis

Yunwei Ren, Jason D. Lee

The information exponent ([BAGJ21]) and its extensions -- which are equivalent to the lowest degree in the Hermite expansion of the link function (after a potential label transform…

cs.LG2025

Transformers Learn to Implement Multi-step Gradient Descent with Chain of Thought

Jianhao Huang, Zixuan Wang, Jason D. Lee

Chain of Thought (CoT) prompting has been shown to significantly improve the performance of large language models (LLMs), particularly in arithmetic and reasoning tasks, by instruc…

cs.LG2024

Learning and Transferring Sparse Contextual Bigrams with Linear Transformers

Yunwei Ren, Zixuan Wang, Jason D. Lee

Transformers have excelled in natural language modeling and one reason behind this success is their exceptional ability to combine contextual informal and global knowledge. However…