Denny Wu
28 papers · 2019–2025 · 5 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 ↓+10 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (37) π Academic Marathon Β· Sprint π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π€
Dynamic Duo
(21)
π¬
Deep Specialist
(11)
π
Keyword Champion
(7)
π
Triple Crown
β‘
Prolific Year Β· Productive
π₯
Unstoppable Β· Bronze
β
The Questioner
(2)
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(124)
Top co-authors
Research topics
Machine Learning
(26)
Optimization & Theory Β· Machine Learning
(25)
Deep Learning
(17)
Optimization & Theory Β· Deep Learning
(12)
Core Methods
(9)
Architectures
(7)
Artificial Intelligence
(5)
Mathematics & Optimization
(4)
Core AI
(4)
Learning Types Β· Deep Learning
(3)
Optimization
(3)
Learning Types Β· Machine Learning
(2)
Natural Language Processing
(1)
Application Areas
(1)
Bayesian & Probabilistic
(1)
Keywords
neural network
(12)
gradient descent
(8)
single-index model
(7)
mean-field langevin dynamics
(6)
feature learning
(6)
sample complexity
(5)
representation learning
(4)
stochastic gradient descent
(3)
two-layer neural network
(3)
mean field theory
(2)
gradient-based optimization
(2)
information exponent
(2)
spiked covariance
(2)
in-context learning
(2)
variance reduction
(2)
double descent
(2)
maximum mean discrepancy
(2)
neural network optimization
(2)
ridge regression
(2)
transformer
(2)
Papers
Learning Compositional Functions with Transformers from Easy-to-Hard Data
COLT 2025
Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
ICLR 2025
Mean-field analysis of polynomial-width two-layer neural network beyond finite time horizon
COLT 2025
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
ICML 2025
Nonlinear transformers can perform inference-time feature learning
ICML 2025
Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
ICLR 2024
Learning sum of diverse features: computational hardness and efficient gradient-based training for ridge combinations
COLT 2024
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
NeurIPS 2024
Nonlinear spiked covariance matrices and signal propagation in deep neural networks
COLT 2024
Pretrained Transformer Efficiently Learns Low-Dimensional Target Functions In-Context
NeurIPS 2024
SILVER: Single-loop variance reduction and application to federated learning
ICML 2024
Why is parameter averaging beneficial in SGD? An objective smoothing perspective
AISTATS 2024
Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction
NeurIPS 2023
Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond
NeurIPS 2023
Gradient-Based Feature Learning under Structured Data
NeurIPS 2023
Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective
NeurIPS 2023
Primal and Dual Analysis of Entropic Fictitious Play for Finite-sum Problems
ICML 2023
Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics
ICLR 2023
Convex Analysis of the Mean Field Langevin Dynamics
AISTATS 2022
High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation
NeurIPS 2022
Particle Stochastic Dual Coordinate Ascent: Exponential convergent algorithm for mean field neural network optimization
ICLR 2022
Two-layer neural network on infinite dimensional data: global optimization guarantee in the mean-field regime
NeurIPS 2022
Understanding the Variance Collapse of SVGD in High Dimensions
ICLR 2022
Particle Dual Averaging: Optimization of Mean Field Neural Network with Global Convergence Rate Analysis
NeurIPS 2021
When does preconditioning help or hurt generalization?
ICLR 2021
Generalization of Two-layer Neural Networks: An Asymptotic Viewpoint
ICLR 2020
On the Optimal Weighted β_2 Regularization in Overparameterized Linear Regression
NeurIPS 2020
Post Selection Inference with Incomplete Maximum Mean Discrepancy Estimator
ICLR 2019