← Authors

Song Mei

26 papers · 2017–2025 · 4 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (4) πŸƒ Academic Marathon (8) 🐝 Cross-Pollinator (9) 🌈 Renaissance Researcher (7) πŸ—ΊοΈ Taxonomy Completionist (36) πŸ‘‘ Triple Crown πŸ† Keyword Champion (2) 🀝 Dynamic Duo (14) ⚑ Prolific Year (7) πŸ—ƒοΈ Keyword Collector (76) πŸ’Ž Century Club (26) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (7) ❓ The Questioner (4)

Conferences

NIPS (10) ICLR (7) ICML (6) COLT (3)

Top co-authors

Yu Bai (14) Theodor Misiakiewicz (6) Caiming Xiong (6) Huan Wang (6) Andrea Montanari (5) Fan Chen (3) Ziang Song (3) Yuhang Cai (2) Behrooz Ghorbani (2) Chi Jin (2)

Keywords

neural network (4) sample complexity (3) extensive-form game (3) neural tangent kernel (3) kernel methods (3) random feature (2) stochastic gradient descent (2) game theory (2) two-layer network (2) statistical learning (2) generalization error (2) correlated equilibrium (2) ridge regression (1) feature learning (1) in-context learning (1) attention mechanism (1) image classification (1) equilibrium learning (1) logistic regression (1) imperfect information (1)

Papers

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models ICLR 2025
Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks ICML 2025
Improving LLM Safety Alignment with Dual-Objective Optimization ICML 2025
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining ICLR 2024
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations ICLR 2024
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm NIPS 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization NIPS 2024
Lower Bounds for Learning in Revealing POMDPs ICML 2023
Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms ICLR 2023
What can a Single Attention Layer Learn? A Study Through the Random Features Lens NIPS 2023
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection NIPS 2023
The Three Stages of Learning Dynamics in High-dimensional Kernel Methods ICLR 2022
Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games NIPS 2022
Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent NIPS 2022
Learning with convolution and pooling operations in kernel methods NIPS 2022
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently? ICLR 2022
Efficient and Differentiable Conformal Prediction with General Function Classes ICLR 2022
Near-Optimal Learning of Extensive-Form Games with Imperfect Information ICML 2022
Learning with invariances in random features and kernel models COLT 2021
Understanding the Under-Coverage Bias in Uncertainty Estimation NIPS 2021
Don’t Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification ICML 2021
Exact Gap between Generalization Error and Uniform Convergence in Random Feature Models ICML 2021
When Do Neural Networks Outperform Kernel Methods? NIPS 2020
Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit COLT 2019
Limitations of Lazy Training of Two-layers Neural Network NIPS 2019
Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality COLT 2017