Song Mei

Publication Activity (10 Years)

Years Active: 2003-2024
Publications (10 Years): 65

Top Topics

Diffusion Models

Regret Minimization

Efficient Learning

Top Venues

Publications

Leo Zhou, Joao Basso, Song Mei
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm. CoRR (2024)
Song Mei
U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models. CoRR (2024)
Licong Lin, Yu Bai, Song Mei
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining. ICLR (2024)
Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations. ICLR (2024)
Ruiqi Zhang, Licong Lin, Yu Bai, Song Mei
Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning. CoRR (2024)
Yuhang Cai, Jingfeng Wu, Song Mei, Michael Lindsey, Peter L. Bartlett
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization. CoRR (2024)
Minshuo Chen, Song Mei, Jianqing Fan, Mengdi Wang
An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization. CoRR (2024)
Yu Bai, Fan Chen, Huan Wang, Caiming Xiong, Song Mei
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection. NeurIPS (2023)
Kai Peng, Tong Lu, Song Mei, Nannan Xue, Yongchao Shen, Menglan Hu
Fine-grained IoT device identification method based on self-supervised ViT. ISPA/BDCloud/SocialCom/SustainCom (2023)
Fan Chen, Yu Bai, Song Mei
Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms. ICLR (2023)
Song Mei, Yuchen Wu
Deep Networks as Denoising Algorithms: Sample-Efficient Learning of Diffusion Models in High-Dimensional Graphical Models. CoRR (2023)
Tianyu Guo, Wei Hu, Song Mei, Huan Wang, Caiming Xiong, Silvio Savarese, Yu Bai
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations. CoRR (2023)
Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai
Lower Bounds for Learning in Revealing POMDPs. CoRR (2023)
Fan Chen, Huan Wang, Caiming Xiong, Song Mei, Yu Bai
Lower Bounds for Learning in Revealing POMDPs. ICML (2023)
Hengyu Fu, Tianyu Guo, Yu Bai, Song Mei
What can a Single Attention Layer Learn? A Study Through the Random Features Lens. CoRR (2023)
Michael Celentano, Zhou Fan, Licong Lin, Song Mei
Mean-field variational inference with the TAP free energy: Geometric and statistical properties in linear models. CoRR (2023)
Licong Lin, Yu Bai, Song Mei
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining. CoRR (2023)
Yu Bai, Fan Chen, Huan Wang, Caiming Xiong, Song Mei
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection. CoRR (2023)
Hengyu Fu, Tianyu Guo, Yu Bai, Song Mei
What can a Single Attention Layer Learn? A Study Through the Random Features Lens. NeurIPS (2023)
Ziang Song, Song Mei, Yu Bai
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently? ICLR (2022)
Joao Basso, David Gamarnik, Song Mei, Leo Zhou
Performance and limitations of the QAOA at constant levels on large sparse hypergraphs and spin glass models. CoRR (2022)
Song Mei, Cong Zhen
A Novel Location Free Link Prediction in Multiplex Social Networks. CoRR (2022)
Yu Bai, Chi Jin, Song Mei, Tiancheng Yu
Near-Optimal Learning of Extensive-Form Games with Imperfect Information. CoRR (2022)
Theodor Misiakiewicz, Song Mei
Learning with convolution and pooling operations in kernel methods. NeurIPS (2022)
Nikhil Ghosh, Song Mei, Bin Yu
The Three Stages of Learning Dynamics in High-dimensional Kernel Methods. ICLR (2022)
Yu Bai, Chi Jin, Song Mei, Ziang Song, Tiancheng Yu
Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent. NeurIPS (2022)
Song Mei, Zhiqiang Ye
Plausible deniability for privacy-preserving data synthesis. CoRR (2022)
Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong
Efficient and Differentiable Conformal Prediction with General Function Classes. CoRR (2022)
Wenxuan Zhao, Zhigang Ju, Hongxi Shi, Song Mei, Yaqiang Zheng
Screening and Efficacy Evaluation of High-Yielding Manganese Peroxidase Strain. BECB (2022)
Wenxuan Zhao, Yaqiang Zheng, Zhigang Ju, Song Mei, Hongxi Shi
High-Yielding Laccase Strain Breeding and Optimization of Fermentation Conditions. BECB (2022)
Wenxuan Zhao, Hongguan Jiao, Zhigang Ju, Yaqiang Zheng, Hongxi Shi, Song Mei
Research on Craft Optimization of Wheat Straw Pretreatment. BECB (2022)
Yu Bai, Chi Jin, Song Mei, Ziang Song, Tiancheng Yu
Efficient Φ-Regret Minimization in Extensive-Form Games via Online Mirror Descent. CoRR (2022)
Taejoo Ahn, Licong Lin, Song Mei
Near-optimal multiple testing in Bayesian linear models with finite-sample FDR control. CoRR (2022)
Ziang Song, Song Mei, Yu Bai
Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games. CoRR (2022)
Yu Bai, Chi Jin, Song Mei, Tiancheng Yu
Near-Optimal Learning of Extensive-Form Games with Imperfect Information. ICML (2022)
Yu Bai, Song Mei, Huan Wang, Yingbo Zhou, Caiming Xiong
Efficient and Differentiable Conformal Prediction with General Function Classes. ICLR (2022)
Fan Chen, Yu Bai, Song Mei
Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms. CoRR (2022)
Fan Chen, Song Mei, Yu Bai
Unified Algorithms for RL with Decision-Estimation Coefficients: No-Regret, PAC, and Reward-Free Learning. CoRR (2022)
Wenxuan Zhao, Zhigang Ju, Yaqiang Zheng, Hongxi Shi, Song Mei
Extraction, Composition Analysis and Blood Lipid Lowering Activity of Rana chensinensis Ovum Oil. BECB (2022)
Joao Basso, David Gamarnik, Song Mei, Leo Zhou
Performance and limitations of the QAOA at constant levels on large sparse hypergraphs and spin glass models. FOCS (2022)
Ziang Song, Song Mei, Yu Bai
Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games. NeurIPS (2022)
Wenxuan Zhao, Zhigang Ju, Yaqiang Zheng, Song Mei, Hongxi Shi
Breeding and Efficiency Evaluation of a High-Yielding Cellobiohydrolase Strain. BECB (2022)
Zitong Yang, Yu Bai, Song Mei
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models. CoRR (2021)
Ziang Song, Song Mei, Yu Bai
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently? CoRR (2021)
Theodor Misiakiewicz, Song Mei
Learning with convolution and pooling operations in kernel methods. CoRR (2021)
Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification. ICML (2021)
Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification. CoRR (2021)
Song Mei, Theodor Misiakiewicz, Andrea Montanari
Learning with invariances in random features and kernel models. COLT (2021)
Michael Celentano, Zhou Fan, Song Mei
Local convexity of the TAP free energy and AMP convergence for Z2-synchronization. CoRR (2021)
Song Mei, Theodor Misiakiewicz, Andrea Montanari
Learning with invariances in random features and kernel models. CoRR (2021)
Zitong Yang, Yu Bai, Song Mei
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models. ICML (2021)
Nikhil Ghosh, Song Mei, Bin Yu
The Three Stages of Learning Dynamics in High-Dimensional Kernel Methods. CoRR (2021)
Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Understanding the Under-Coverage Bias in Uncertainty Estimation. NeurIPS (2021)
Song Mei
Research on the Patriotic Education for College Students in the New Era: Taking the Enhancement of Cultural Confidence as an Example. CIPAE (2021)
Yu Bai, Song Mei, Huan Wang, Caiming Xiong
Understanding the Under-Coverage Bias in Uncertainty Estimation. CoRR (2021)
Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari
When Do Neural Networks Outperform Kernel Methods? NeurIPS (2020)
Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari
When Do Neural Networks Outperform Kernel Methods? CoRR (2020)
Song Mei, Theodor Misiakiewicz, Andrea Montanari
Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit. CoRR (2019)
Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari
Linearized two-layers neural networks in high dimension. CoRR (2019)
Song Mei, Theodor Misiakiewicz, Andrea Montanari
Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit. COLT (2019)
Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari
Limitations of Lazy Training of Two-layers Neural Network. NeurIPS (2019)
Behrooz Ghorbani, Song Mei, Theodor Misiakiewicz, Andrea Montanari
Limitations of Lazy Training of Two-layers Neural Networks. CoRR (2019)
Yu Bai, John C. Duchi, Song Mei
Proximal algorithms for constrained composite optimization, with applications to solving low-rank SDPs. CoRR (2019)
Song Mei, Andrea Montanari, Phan-Minh Nguyen
A Mean Field View of the Landscape of Two-Layers Neural Networks. CoRR (2018)
Song Mei, Theodor Misiakiewicz, Andrea Montanari, Roberto Imbuzeiro Oliveira
Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality. COLT (2017)
Song Mei, Pingwen Zhang
On a Molecular Based Q-Tensor Model for Liquid Crystals with Density Variations. Multiscale Model. Simul. 13 (3) (2015)
Yunhe Zhang, Zhitang Li, Song Mei, Cai Fu
Session-Based Tunnel Scheduling Model in Multi-link Aggregate IPSec VPN. MUE (2009)
Li Xu, Hui Bo, Haixia Liu, Mingqiang Yang, Song Mei, Guo Wei
Research and Analysis of Topology Control in NS-2 for Ad-hoc Wireless Network. CISIS (2008)
Song Mei
New Well Design of Hydrological Network Information System Based on GIS. ISCSCT (1) (2008)
Zhanjun Chang, Song Mei, Zheng Gu, Jianqin Gu, Liangxiao Xia, Shuang Liang, Jiarui Lin
Realization of integration and working procedure on digital hospital information system. Comput. Stand. Interfaces 25 (5) (2003)