381 citations · 1.4k across the 100 of their papers we have counts for
61 papers · 1 filter
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
Martin Bertran, Shuai Tang, Michael Kearns +3
Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as…
Membership Inference Attacks on Diffusion Models via Quantile Regression
Shuai Tang, Zhiwei Steven Wu, Sergul Aydore +2
Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private inform…
On the Sublinear Regret of GP-UCB
Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas
In the kernelized bandit problem, a learner aims to sequentially compute the optimum of a function lying in a reproducing kernel Hilbert space given only noisy evaluations at seque…
Scalable Membership Inference Attacks via Quantile Regression
Martin Bertran, Shuai Tang, Michael Kearns +3
Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can…
Meta-Learning Adversarial Bandit Algorithms
Mikhail Khodak, Ilya Osadchiy, Keegan Harris +4
We study online meta-learning with bandit feedback, with the goal of improving performance across multiple tasks if they are similar according to some natural similarity measure. A…
Adaptive Principal Component Regression with Applications to Panel Data
Anish Agarwal, Keegan Harris, Justin Whitehouse +1
Principal component regression (PCR) is a popular technique for fixed-design error-in-variables regression, a generalization of the linear regression setting in which the observed…
Inverse Reinforcement Learning without Reinforcement Learning
Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell +1
Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunat…
Improved Differentially Private Regression via Gradient Boosting
Shuai Tang, Sergul Aydore, Michael Kearns +5
We revisit the problem of differentially private squared error linear regression. We observe that existing state-of-the-art methods are sensitive to the choice of hyperparameters -…
Federated Learning as a Network Effects Game
Shengyuan Hu, Dung Daniel Ngo, Shuran Zheng +2
Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data. Although there h…
Counterfactual Prediction Under Outcome Measurement Error
Luke Guerdan, Amanda Coston, Kenneth Holstein +1
Across domains such as medicine, employment, and criminal justice, predictive models often target labels that imperfectly reflect the outcomes of interest to experts and policymake…
Reinforcement Learning with Stepwise Fairness Constraints
Zhun Deng, He Sun, Zhiwei Steven Wu +2
AI methods are used in societally important settings, ranging from credit to employment to housing, and it is crucial to provide fairness in regard to algorithmic decision making.…
Private Synthetic Data for Multitask Learning and Marginal Queries
Giuseppe Vietri, Cedric Archambeau, Sergul Aydore +6
We provide a differentially private algorithm for producing synthetic data simultaneously useful for multiple tasks: marginal queries and multitask machine learning (ML). A key inn…
Sequence Model Imitation Learning with Unobserved Contexts
Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell +1
We consider imitation learning problems where the learner's ability to mimic the expert increases throughout the course of an episode as more information is revealed. One example o…
Private Synthetic Data with Hierarchical Structure
Terrance Liu, Zhiwei Steven Wu
We study the problem of differentially private synthetic data generation for hierarchical datasets in which individual data points are grouped together (e.g., people within househo…
On Privacy and Personalization in Cross-Silo Federated Learning
Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu +1
While the application of differential privacy (DP) has been well-studied in cross-device federated learning (FL), there is a lack of work considering DP and its implications for cr…
Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints
Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas +1
There is a disconnect between how researchers and practitioners handle privacy-utility tradeoffs. Researchers primarily operate from a privacy first perspective, setting strict pri…
Incentivizing Combinatorial Bandit Exploration
Xinyan Hu, Dung Daniel Ngo, Aleksandrs Slivkins +1
Consider a bandit algorithm that recommends actions to self-interested users in a recommendation system. The users are free to choose other actions and need to be incentivized to f…
Meta-Learning Adversarial Bandits
Maria-Florina Balcan, Keegan Harris, Mikhail Khodak +1
We study online learning with bandit feedback across multiple tasks, with the goal of improving average performance across tasks if they are similar according to some natural task-…
Minimax Optimal Online Imitation Learning via Replay Estimation
Gokul Swamy, Nived Rajaraman, Matthew Peng +5
Online imitation learning is the problem of how best to mimic expert demonstrations, given access to the environment or an accurate simulator. Prior work has shown that in the infi…
A Sandbox Tool to Bias(Stress)-Test Fairness Algorithms
Nil-Jana Akpinar, Manish Nagireddy, Logan Stapleton +4
Motivated by the growing importance of reducing unfairness in ML predictions, Fair-ML researchers have presented an extensive suite of algorithmic 'fairness-enhancing' remedies. Mo…
Fair Federated Learning via Bounded Group Loss
Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith
Fair prediction across protected groups is an important constraint for many federated learning applications. However, prior work studying group fair federated learning lacks formal…
Fully Adaptive Composition in Differential Privacy
Justin Whitehouse, Aaditya Ramdas, Ryan Rogers +1
Composition is a key feature of differential privacy. Well-known advanced composition theorems allow one to query a private database quadratically more times than basic privacy com…
Causal Imitation Learning under Temporally Correlated Noise
Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell +1
We develop algorithms for imitation learning from policy data that was corrupted by temporally correlated noise in expert actions. When noise affects multiple timesteps of recorded…
Improved Regret for Differentially Private Exploration in Linear MDP
Dung Daniel Ngo, Giuseppe Vietri, Zhiwei Steven Wu
We study privacy-preserving exploration in sequential decision-making for environments that rely on sensitive data such as medical records. In particular, we focus on solving the p…