Song Mei
26 papers · 2017–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (47) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π€
Dynamic Duo
(14)
π
Keyword Champion
(2)
π
Triple Crown
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
(4)
π
Century Club Β· Bronze
π
Renaissance Researcher
(5)
ποΈ
Keyword Collector
(110)
Venues
Top co-authors
Research topics
Machine Learning
(21)
Optimization & Theory Β· Machine Learning
(20)
Deep Learning
(8)
Core Methods
(8)
Artificial Intelligence
(7)
Core AI
(6)
Architectures
(5)
Mathematics & Optimization
(4)
Reinforcement Learning
(4)
Learning Types Β· Machine Learning
(4)
Mathematics
(3)
Methods
(3)
Optimization
(3)
Optimization & Theory Β· Deep Learning
(3)
Learning Types Β· Deep Learning
(2)
Keywords
sample complexity
(5)
kernel methods
(4)
neural network
(4)
generalization error
(3)
correlated equilibrium
(3)
extensive-form game
(3)
neural tangent kernel
(3)
stochastic gradient descent
(3)
two-layer network
(2)
random feature
(2)
prediction interval
(2)
implicit bia
(2)
partially observable markov decision process
(2)
non-homogeneous networks
(2)
nash equilibrium
(2)
reinforcement learning
(2)
game theory
(2)
statistical learning
(2)
in-context learning
(2)
gradient descent
(2)
Papers
Implicit Bias of Gradient Descent for Non-Homogeneous Deep Networks
ICML 2025
Improving LLM Safety Alignment with Dual-Objective Optimization
ICML 2025
U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models
ICLR 2025
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
ICLR 2024
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
NeurIPS 2024
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
NeurIPS 2024
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
ICLR 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
Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection
NeurIPS 2023
What can a Single Attention Layer Learn? A Study Through the Random Features Lens
NeurIPS 2023
Efficient and Differentiable Conformal Prediction with General Function Classes
ICLR 2022
Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent
NeurIPS 2022
Learning with convolution and pooling operations in kernel methods
NeurIPS 2022
Near-Optimal Learning of Extensive-Form Games with Imperfect Information
ICML 2022
Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games
NeurIPS 2022
The Three Stages of Learning Dynamics in High-dimensional Kernel Methods
ICLR 2022
When Can We Learn General-Sum Markov Games with a Large Number of Players Sample-Efficiently?
ICLR 2022
Donβt 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
Learning with invariances in random features and kernel models
COLT 2021
Understanding the Under-Coverage Bias in Uncertainty Estimation
NeurIPS 2021
When Do Neural Networks Outperform Kernel Methods?
NeurIPS 2020
Limitations of Lazy Training of Two-layers Neural Network
NeurIPS 2019
Mean-field theory of two-layers neural networks: dimension-free bounds and kernel limit
COLT 2019
Solving SDPs for synchronization and MaxCut problems via the Grothendieck inequality
COLT 2017