In the kernelized bandit problem, a learner aims to sequentially compute...
We study how to release summary statistics on a data stream subject to t...
Membership inference attacks are designed to determine, using black box
...
We study online meta-learning with bandit feedback, with the goal of
imp...
Principal component regression (PCR) is a popular technique for fixed-de...
In many practical applications of differential privacy, practitioners se...
Algorithmic decision-making in high-stakes domains often involves assign...
We study the problem of efficiently generating differentially private
sy...
Inverse Reinforcement Learning (IRL) is a powerful set of techniques for...
We revisit the problem of differentially private squared error linear
re...
Differentially private stochastic gradient descent privatizes model trai...
Across domains such as medicine, employment, and criminal justice, predi...
Federated Learning (FL) aims to foster collaboration among a population ...
A growing literature on human-AI decision-making investigates strategies...
We propose a framework for decision-making in the presence of strategic
...
AI methods are used in societally important settings, ranging from credi...
A reconstruction attack on a private dataset D takes as input some publi...
In the literature on game-theoretic equilibrium finding, focus has mainl...
We provide a differentially private algorithm for producing synthetic da...
A variety of problems in econometrics and machine learning, including
in...
We consider imitation learning problems where the expert has access to a...
While the application of differential privacy (DP) has been well-studied...
There is a disconnect between how researchers and practitioners handle
p...
We study the problem of differentially private synthetic data generation...
Consider a bandit algorithm that recommends actions to self-interested u...
Online imitation learning is the problem of how best to mimic expert
dem...
We study online learning with bandit feedback across multiple tasks, wit...
Child welfare agencies across the United States are turning to data-driv...
Recent years have seen the development of many open-source ML fairness
t...
This is an extended analysis of our paper "How Child Welfare Workers Red...
AI-based decision support tools (ADS) are increasingly used to augment h...
In federated learning, fair prediction across various protected groups (...
Composition is a key feature of differential privacy. Well-known advance...
This work derives methods for performing nonparametric, nonasymptotic
st...
Large-scale machine learning systems often involve data distributed acro...
We develop algorithms for imitation learning from policy data that was
c...
We study privacy-preserving exploration in sequential decision-making fo...
Safe reinforcement learning (RL) aims to learn policies that satisfy cer...
When subjected to automated decision-making, decision subjects may
strat...
Recent work by Jarrett et al. attempts to frame the problem of offline
i...
Many problems in machine learning rely on multi-task learning (MTL), in ...
Randomized experiments can be susceptible to selection bias due to poten...
Machine Learning algorithms often prompt individuals to strategically mo...
Providing privacy protection has been one of the primary motivations of
...
We study private synthetic data generation for query release, where the ...
Automated decision-making tools increasingly assess individuals to deter...
We provide a unifying view of a large family of previous imitation learn...
We study the effects of information discrepancy across sub-populations o...
As machine learning black boxes are increasingly being deployed in criti...
In many statistical problems, incorporating priors can significantly imp...