Lei Wu
33 papers · 2009–2026 · 13 venues · across top CS/AI venues
This profile combines several different researchers. Authors are keyed by name, and this name's papers fall into 18 separate collaboration groups - the largest holds only 24% of them. Pick the group below that matches the researcher you mean. How a shared name is split.
Achievements are not shown for a combined profile - each one describes a single researcher's record, which this is not.
Which Lei Wu?
8 groups of papers that share co-authors internally but none with each other - each most likely a different researcher. Pick one to see its papers.
with Mingze Wang, Weinan E, Chao Ma
8 papers
· 2018–2026
· NeurIPS, ICML, COLT
Hide ▲
Optimal Learning Rate Schedules under Functional Scaling Laws: Power Decay and Warmup–Stable–Decay (Extended Abstract)
COLT 2026
The Sharpness Disparity Principle in Transformers for Accelerating Language Model Pre-Training
ICML 2025
Achieving Margin Maximization Exponentially Fast via Progressive Norm Rescaling
ICML 2024
Improving Generalization and Convergence by Enhancing Implicit Regularization
NeurIPS 2024
Parameter Symmetry and Noise Equilibrium of Stochastic Gradient Descent
NeurIPS 2024
The alignment property of SGD noise and how it helps select flat minima: A stability analysis
NeurIPS 2022
Global Convergence of Gradient Descent for Deep Linear Residual Networks
NeurIPS 2019
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective
NeurIPS 2018
10 papers whose co-authors appear nowhere else under this name
ArtPro: Self-Supervised Articulated Object Reconstruction with Adaptive Integration of Mobility Proposals
CVPR 2026
Backdooring Rationalization
AAAI 2026
Analyzing the Role of Permutation Invariance in Linear Mode Connectivity
AISTATS 2025
Why Do You Grok? A Theoretical Analysis on Grokking Modular Addition
ICML 2024
RZCR: Zero-shot Character Recognition via Radical-based Reasoning
IJCAI 2023
The Implicit Regularization of Dynamical Stability in Stochastic Gradient Descent
ICML 2023
Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks
NeurIPS 2023
A spectral-based analysis of the separation between two-layer neural networks and linear methods
JMLR 2022
Learning a Single Neuron for Non-monotonic Activation Functions
AISTATS 2022
Learning Bregman Distance Functions and Its Application for Semi-Supervised Clustering
NeurIPS 2009