Weiwei Kong
6 papers · 2019–2026 · 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 ↓+2 more ↓ Show less ↑
🌉 Interdisciplinary Bridge · Silver 🏃 Academic Marathon · Sprint 🗺️ Taxonomy Completionist (11) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Bronze
🏆
Keyword Champion
🌈
Renaissance Researcher
(5)
Venues
Top co-authors
Research topics
Machine Learning
(5)
Optimization & Theory
(4)
Application Areas
(2)
Learning Types · Machine Learning
(2)
Artificial Intelligence
(1)
Deep Learning
(1)
Mathematics & Optimization
(1)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Security & Privacy
(1)
Core AI
(1)
Differential Privacy
(1)
Generation
(1)
Learning Types · Deep Learning
(1)
Methods
(1)
Keywords
differential privacy
(3)
combinatorial optimization
(1)
learning theory
(1)
reinforcement learning
(1)
stochastic gradient descent
(1)
in-context learning
(1)
pac learning
(1)
privacy-preserving learning
(1)
empirical risk minimization
(1)
online algorithm
(1)
primal-dual method
(1)
synthetic data
(1)
gradient clipping
(1)
model collapse
(1)
contrastive loss
(1)
adversarial distribution
(1)
softmax function
(1)
simplex projection
(1)
synthetic text generation
(1)
bregman projection
(1)
Papers
Learning from Synthetic Data: Limitations of ERM
ALT 2026
Differentially private optimization for non-decomposable objective functions
ICLR 2025
Private prediction for large-scale synthetic text generation
EMNLP 2024
A Unified Fast Gradient Clipping Framework for DP-SGD
NeurIPS 2023
Rankmax: An Adaptive Projection Alternative to the Softmax Function
NeurIPS 2020
A new dog learns old tricks: RL finds classic optimization algorithms
ICLR 2019