activity
20122025
most citedGeneralized Fisher Score for Feature Selection

462 citations · 767 across the 20 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG2025

Higher-order Linear Attention

Yifan Zhang, Zhen Qin, Mengdi Wang +1

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (S…

cs.LG20231 cited

Variance-Dependent Regret Bounds for Linear Bandits and Reinforcement Learning: Adaptivity and Computational Efficiency

Heyang Zhao, Jiafan He, Dongruo Zhou +2

Recently, several studies (Zhou et al., 2021a; Zhang et al., 2021b; Kim et al., 2021; Zhou and Gu, 2022) have provided variance-dependent regret bounds for linear contextual bandit…

cs.LG20239 cited

Structure-informed Language Models Are Protein Designers

Zaixiang Zheng, Yifan Deng, Dongyu Xue +3

This paper demonstrates that language models are strong structure-based protein designers. We present LM-Design, a generic approach to reprogramming sequence-based protein language…

cs.LG2022

Learning Two-Player Mixture Markov Games: Kernel Function Approximation and Correlated Equilibrium

Chris Junchi Li, Dongruo Zhou, Quanquan Gu +1

We consider learning Nash equilibria in two-player zero-sum Markov Games with nonlinear function approximation, where the action-value function is approximated by a function in a R…

cs.LG202223 cited

Towards Understanding Mixture of Experts in Deep Learning

Zixiang Chen, Yihe Deng, Yue Wu +2

The Mixture-of-Experts (MoE) layer, a sparsely-activated model controlled by a router, has achieved great success in deep learning. However, the understanding of such architecture…

cs.LG20222 cited

The Power and Limitation of Pretraining-Finetuning for Linear Regression under Covariate Shift

Jingfeng Wu, Difan Zou, Vladimir Braverman +2

We study linear regression under covariate shift, where the marginal distribution over the input covariates differs in the source and the target domains, while the conditional dist…