Pengkun Yang
10 papers · 2019–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge π Cross-Pollinator (15) πΊοΈ Taxonomy Completionist (19) π§ Keyword Pioneer π Conference Polyglot (5)
π
Academic Marathon
(6)
π
Keyword Champion
(2)
π
Century Club
(10)
π₯
Unstoppable
(5)
Conferences
COLT (4)
AAAI (2)
NIPS (2)
ICML (1)
JMLR (1)
Top co-authors
Keywords
over-parameterized neural network
(2)
active learning
(2)
gradient descent
(2)
federated learning
(2)
adversarial robustness
(1)
convergence analysis
(1)
distributed optimization
(1)
reproducing kernel hilbert space
(1)
non-parametric regression
(1)
linear regression
(1)
probability measure
(1)
exact recovery
(1)
deep neural network
(1)
relu activation
(1)
data heterogeneity
(1)
data selection
(1)
gradient norm
(1)
uncertainty estimation
(1)
statistical efficiency
(1)
residual network
(1)
Papers
Sample Complexity of Correlation Detection in the Gaussian Wigner Model
ICML 2025
Fast and Multiphase Rates for Nearest Neighbor Classifiers
COLT 2025
Identifiability and Estimation in High-Dimensional Nonparametric Latent Structure Models
COLT 2025
Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
COLT 2024
Deep Active Learning with Noise Stability
AAAI 2024
A Non-parametric View of FedAvg and FedProx:Beyond Stationary Points
JMLR 2023
Boosting Active Learning via Improving Test Performance
AAAI 2022
Global Convergence of Federated Learning for Mixed Regression
NIPS 2022
Modeling from Features: a Mean-field Framework for Over-parameterized Deep Neural Networks
COLT 2021
On Learning Over-parameterized Neural Networks: A Functional Approximation Perspective
NIPS 2019