Lifeng LAI
10 papers · 2021–2025 · 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Silver π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (23) π£ Hot Topic Early Bird π Grand Slam
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(9)
Optimization & Theory
(5)
Artificial Intelligence
(4)
Mathematics & Optimization
(4)
Core AI
(4)
Core Methods
(4)
Optimization
(4)
Deep Learning
(2)
Learning Types
(2)
Data Science & Analytics
(1)
Reinforcement Learning
(1)
Application Areas
(1)
Applications
(1)
Architectures
(1)
Learning Paradigms
(1)
Keywords
optimal transport
(3)
action poisoning
(2)
wasserstein distance
(2)
adversarial attack
(2)
block coordinate descent
(2)
riemannian optimization
(2)
stiefel manifold
(2)
metric learning
(1)
risk minimization
(1)
reinforcement learning
(1)
mean estimation
(1)
coordinate descent
(1)
exploration
(1)
implicit differentiation
(1)
sample complexity
(1)
multi-agent reinforcement learning
(1)
black-box attack
(1)
bilevel optimization
(1)
k-nearest neighbor
(1)
in-context learning
(1)
Papers
Efficiently Escaping Saddle Points in Bilevel Optimization
JMLR 2025
Transformers Handle Endogeneity in In-Context Linear Regression
ICLR 2025
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
NeurIPS 2024
On the Convergence of Projected Alternating Maximization for Equitable and Optimal Transport
JMLR 2024
Risk-Sensitive Reward-Free Reinforcement Learning with CVaR
ICML 2024
Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning
NeurIPS 2023
A Riemannian Block Coordinate Descent Method for Computing the Projection Robust Wasserstein Distance
ICML 2021
Efficient Classification with Adaptive KNN
AAAI 2021
Projection Robust Wasserstein Barycenters
ICML 2021
Provably Efficient Black-Box Action Poisoning Attacks Against Reinforcement Learning
NeurIPS 2021