Pengkun Yang
10 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 ↓+3 more ↓ Show less ↑
🗺️ Taxonomy Completionist (20) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🏆 Keyword Champion (2)
🗃️
Keyword Collector
(53)
🔥
Unstoppable · Bronze
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory
(6)
Deep Learning
(4)
Core Methods
(4)
Mathematics & Optimization
(3)
Learning Types · Machine Learning
(3)
Mathematics
(3)
Artificial Intelligence
(2)
Architectures
(2)
Learning Paradigms · Artificial Intelligence
(2)
Learning Paradigms · Machine Learning
(2)
Computer Science
(1)
Foundations
(1)
Learning Types · Deep Learning
(1)
Techniques
(1)
Keywords
active learning
(2)
overparameterized neural network
(2)
sample size
(2)
federated learning
(2)
gradient descent
(2)
convergence analysis
(1)
generalization error
(1)
adversarial robustness
(1)
nonparametric regression
(1)
relu activation
(1)
semantic segmentation
(1)
linear regression
(1)
nearest neighbor classifier
(1)
probability measure
(1)
minimax rate
(1)
reproducing kernel hilbert space
(1)
exact recovery
(1)
deep neural network
(1)
identifiability
(1)
distributed optimization
(1)
Papers
Fast and Multiphase Rates for Nearest Neighbor Classifiers
COLT 2025
Identifiability and Estimation in High-Dimensional Nonparametric Latent Structure Models
COLT 2025
Sample Complexity of Correlation Detection in the Gaussian Wigner Model
ICML 2025
Deep Active Learning with Noise Stability
AAAI 2024
Information-Theoretic Thresholds for the Alignments of Partially Correlated Graphs
COLT 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
NeurIPS 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
NeurIPS 2019