research
∙
07/05/2023
Jailbroken: How Does LLM Safety Training Fail?
Large language models trained for safety and harmlessness remain suscept...
share
research
∙
07/13/2022
TCT: Convexifying Federated Learning using Bootstrapped Neural Tangent Kernels
State-of-the-art federated learning methods can perform far worse than t...
research
∙
02/11/2022
Predicting Out-of-Distribution Error with the Projection Norm
We propose a metric – Projection Norm – to predict a model's performance...
research
∙
08/19/2021
Learning Equilibria in Matching Markets from Bandit Feedback
Large-scale, two-sided matching platforms must find market outcomes that...
research
∙
02/17/2021
Designing Approximately Optimal Search on Matching Platforms
We study the design of a decentralized two-sided matching market in whic...
research
∙
10/22/2020
Optimal Robustness-Consistency Trade-offs for Learning-Augmented Online Algorithms
We study the problem of improving the performance of online algorithms b...
research
∙
05/28/2020
Better and Simpler Learning-Augmented Online Caching
Lykouris and Vassilvitskii (ICML 2018) introduce a model of online cachi...
research
∙
07/19/2018