3 papers
math.LO2026
Strong marker sets for arbitrary generating sets
Su Gao, Tianhao Wang
We prove the existence of clopen strong marker sets in for arbitrary finite generating sets. Specifically, for any positive integers and any fi…
cs.LG2026
Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model
Siyu Chen, Beining Wu, Miao Lu +2
In this work, we tackle the following question: Can neural networks trained with gradient-based methods achieve the optimal computational-statistical tradeoff in learning Gaussian…
cs.LG2025
Taming Polysemanticity in LLMs: Provable Feature Recovery via Sparse Autoencoders
Siyu Chen, Heejune Sheen, Xuyuan Xiong +2
We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training…