Alexander Wei
7 papers · 2020–2024 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (2) π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (17)
π
Cross-Pollinator
(9)
π
Renaissance Researcher
(6)
π₯
Unstoppable
(5)
β
The Questioner
Conferences
NIPS (4)
ICML (3)
Top co-authors
Keywords
federated learning
(1)
neural tangent kernel
(1)
feature learning
(1)
non-convex optimization
(1)
convex optimization
(1)
kernel regression
(1)
machine learning
(1)
neural representation
(1)
random matrix theory
(1)
multi-armed bandit
(1)
regret bound
(1)
online algorithm
(1)
data heterogeneity
(1)
learning-augmented algorithm
(1)
lower bound
(1)
scaling law
(1)
out-of-distribution detection
(1)
competitive analysis
(1)
machine learning prediction
(1)
adversarial example
(1)
Papers
Covert Malicious Finetuning: Challenges in Safeguarding LLM Adaptation
ICML 2024
Jailbroken: How Does LLM Safety Training Fail?
NIPS 2023
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
NIPS 2022
More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize
ICML 2022
Predicting Out-of-Distribution Error with the Projection Norm
ICML 2022
Learning Equilibria in Matching Markets from Bandit Feedback
NIPS 2021
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
NIPS 2020