works on

From the 1 of 25 linked papers with an AI index.

activity
20182025
most citedFine-Grained Analysis of Optimization and Generalization for Overparameterized Two-Layer Neural Networks

256 citations · 457 across the 19 of their papers we have counts for

collaborators

25 papers

cs.LG2025

Non-Asymptotic Length Generalization

Thomas Chen, Tengyu Ma, Zhiyuan Li

Length generalization is the ability of a learning algorithm to learn a hypothesis which generalizes to longer inputs than the inputs in the training set. In this paper, we provide…

cs.LG2025

PENCIL: Long Thoughts with Short Memory

Chenxiao Yang, Nathan Srebro, David McAllester +1

While state-of-the-art LLMs have demonstrated great promise of using long Chains-of-Thought (CoT) to boost reasoning, scaling it up to more challenging problems at test-time is fun…

cs.LG2025

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…

cs.LG2025

Weak-to-Strong Generalization Even in Random Feature Networks, Provably

Marko Medvedev, Kaifeng Lyu, Dingli Yu +3

Weak-to-Strong Generalization (Burns et al., 2024) is the phenomenon whereby a strong student, say GPT-4, learns a task from a weak teacher, say GPT-2, and ends up significantly ou…

cs.LG2024

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…

cs.LG2024

Implicit Bias of AdamW: Norm Constrained Optimization

Shuo Xie, Zhiyuan Li

Adam with decoupled weight decay, also known as AdamW, is widely acclaimed for its superior performance in language modeling tasks, surpassing Adam with regularization in…