Zhiwei Steven Wu

research

∙ 07/14/2023

On the Sublinear Regret of GP-UCB

In the kernelized bandit problem, a learner aims to sequentially compute...

0 Justin Whitehouse, et al. ∙

research

∙ 07/09/2023

Private Data Stream Analysis for Universal Symmetric Norm Estimation

We study how to release summary statistics on a data stream subject to t...

0 Vladimir Braverman, et al. ∙

research

∙ 07/07/2023

Scalable Membership Inference Attacks via Quantile Regression

Membership inference attacks are designed to determine, using black box ...

0 Martin Bertran, et al. ∙

research

∙ 07/05/2023

Meta-Learning Adversarial Bandit Algorithms

We study online meta-learning with bandit feedback, with the goal of imp...

0 Mikhail Khodak, et al. ∙

research

∙ 07/03/2023

Adaptive Principal Component Regression with Applications to Panel Data

Principal component regression (PCR) is a popular technique for fixed-de...

0 Anish Agarwal, et al. ∙

research

∙ 06/24/2023

Adaptive Privacy Composition for Accuracy-first Mechanisms

In many practical applications of differential privacy, practitioners se...

0 Ryan Rogers, et al. ∙

research

∙ 06/09/2023

Strategic Apple Tasting

Algorithmic decision-making in high-stakes domains often involves assign...

0 Keegan Harris, et al. ∙

research

∙ 06/05/2023

Generating Private Synthetic Data with Genetic Algorithms

We study the problem of efficiently generating differentially private sy...

0 Terrance Liu, et al. ∙

research

∙ 03/26/2023

Inverse Reinforcement Learning without Reinforcement Learning

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for...

0 Gokul Swamy, et al. ∙

research

∙ 03/06/2023

Improved Differentially Private Regression via Gradient Boosting

We revisit the problem of differentially private squared error linear re...

0 Shuai Tang, et al. ∙

research

∙ 03/02/2023

Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance

Differentially private stochastic gradient descent privatizes model trai...

0 Xin Gu, et al. ∙

research

∙ 02/22/2023

Counterfactual Prediction Under Outcome Measurement Error

Across domains such as medicine, employment, and criminal justice, predi...

0 Luke Guerdan, et al. ∙

research

∙ 02/16/2023

Federated Learning as a Network Effects Game

Federated Learning (FL) aims to foster collaboration among a population ...

0 Shengyuan Hu, et al. ∙

research

∙ 02/13/2023

Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making

A growing literature on human-AI decision-making investigates strategies...

0 Luke Guerdan, et al. ∙

research

∙ 11/25/2022

Strategyproof Decision-Making in Panel Data Settings and Beyond

We propose a framework for decision-making in the presence of strategic ...

0 Keegan Harris, et al. ∙

research

∙ 11/08/2022

Reinforcement Learning with Stepwise Fairness Constraints

AI methods are used in societally important settings, ranging from credi...

4 Zhun Deng, et al. ∙

research

∙ 11/06/2022

Confidence-Ranked Reconstruction of Census Microdata from Published Statistics

A reconstruction attack on a private dataset D takes as input some publi...

0 Travis Dick, et al. ∙

research

∙ 09/28/2022

Meta-Learning in Games

In the literature on game-theoretic equilibrium finding, focus has mainl...

0 Keegan Harris, et al. ∙

research

∙ 09/15/2022

Private Synthetic Data for Multitask Learning and Marginal Queries

We provide a differentially private algorithm for producing synthetic da...

8 Giuseppe Vietri, et al. ∙

research

∙ 08/19/2022

Game-Theoretic Algorithms for Conditional Moment Matching

A variety of problems in econometrics and machine learning, including in...

0 Gokul Swamy, et al. ∙

research

∙ 08/03/2022

Sequence Model Imitation Learning with Unobserved Contexts

We consider imitation learning problems where the expert has access to a...

0 Gokul Swamy, et al. ∙

research

∙ 06/16/2022

On Privacy and Personalization in Cross-Silo Federated Learning

While the application of differential privacy (DP) has been well-studied...

0 Ziyu Liu, et al. ∙

research

∙ 06/15/2022

Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints

There is a disconnect between how researchers and practitioners handle p...

0 Justin Whitehouse, et al. ∙

research

∙ 06/13/2022

Private Synthetic Data with Hierarchical Structure

We study the problem of differentially private synthetic data generation...

0 Terrance Liu, et al. ∙

research

∙ 06/01/2022

Incentivizing Combinatorial Bandit Exploration

Consider a bandit algorithm that recommends actions to self-interested u...

0 Xinyan Hu, et al. ∙

research

∙ 05/30/2022

Minimax Optimal Online Imitation Learning via Replay Estimation

Online imitation learning is the problem of how best to mimic expert dem...

0 Gokul Swamy, et al. ∙

research

∙ 05/27/2022

Meta-Learning Adversarial Bandits

We study online learning with bandit feedback across multiple tasks, wit...

0 Maria-Florina Balcan, et al. ∙

research

∙ 05/18/2022

Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders

Child welfare agencies across the United States are turning to data-driv...

0 Logan Stapleton, et al. ∙

research

∙ 05/13/2022

Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits

Recent years have seen the development of many open-source ML fairness t...

0 Wesley Hanwen Deng, et al. ∙

research

∙ 04/29/2022

Extended Analysis of "How Child Welfare Workers Reduce Racial Disparities in Algorithmic Decisions"

This is an extended analysis of our paper "How Child Welfare Workers Red...

0 Logan Stapleton, et al. ∙

research

∙ 04/05/2022

Improving Human-AI Partnerships in Child Welfare: Understanding Worker Practices, Challenges, and Desires for Algorithmic Decision Support

AI-based decision support tools (ADS) are increasingly used to augment h...

0 Anna Kawakami, et al. ∙

research

∙ 03/18/2022

Provably Fair Federated Learning via Bounded Group Loss

In federated learning, fair prediction across various protected groups (...

0 Shengyuan Hu, et al. ∙

research

∙ 03/10/2022

Fully Adaptive Composition in Differential Privacy

Composition is a key feature of differential privacy. Well-known advance...

0 Justin Whitehouse, et al. ∙

research

∙ 02/17/2022

Locally private nonparametric confidence intervals and sequences

This work derives methods for performing nonparametric, nonasymptotic st...

0 Ian Waudby-Smith, et al. ∙

research

∙ 02/10/2022

Personalization Improves Privacy-Accuracy Tradeoffs in Federated Optimization

Large-scale machine learning systems often involve data distributed acro...

11 Alberto Bietti, et al. ∙

research

∙ 02/02/2022

Causal Imitation Learning under Temporally Correlated Noise

We develop algorithms for imitation learning from policy data that was c...

0 Gokul Swamy, et al. ∙

research

∙ 02/02/2022

Improved Regret for Differentially Private Exploration in Linear MDP

We study privacy-preserving exploration in sequential decision-making fo...

0 Dung Daniel Ngo, et al. ∙

research

∙ 01/28/2022

Constrained Variational Policy Optimization for Safe Reinforcement Learning

Safe reinforcement learning (RL) aims to learn policies that satisfy cer...

11 Zuxin Liu, et al. ∙

research

∙ 12/12/2021

Bayesian Persuasion for Algorithmic Recourse

When subjected to automated decision-making, decision subjects may strat...

0 Keegan Harris, et al. ∙

research

∙ 10/05/2021

A Critique of Strictly Batch Imitation Learning

Recent work by Jarrett et al. attempts to frame the problem of offline i...

0 Gokul Swamy, et al. ∙

research

∙ 08/30/2021

Private Multi-Task Learning: Formulation and Applications to Federated Learning

Many problems in machine learning rely on multi-task learning (MTL), in ...

0 Shengyuan Hu, et al. ∙

research

∙ 07/21/2021

Incentivizing Compliance with Algorithmic Instruments

Randomized experiments can be susceptible to selection bias due to poten...

0 Daniel Ngo, et al. ∙

research

∙ 07/12/2021

Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses

Machine Learning algorithms often prompt individuals to strategically mo...

0 Keegan Harris, et al. ∙

research

∙ 06/25/2021

Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy

Providing privacy protection has been one of the primary motivations of ...

0 Xinwei Zhang, et al. ∙

research

∙ 06/14/2021

Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods

We study private synthetic data generation for query release, where the ...

0 Terrance Liu, et al. ∙

research

∙ 06/07/2021

Stateful Strategic Regression

Automated decision-making tools increasingly assess individuals to deter...

0 Keegan Harris, et al. ∙

research

∙ 03/04/2021

Of Moments and Matching: Trade-offs and Treatments in Imitation Learning

We provide a unifying view of a large family of previous imitation learn...

0 Gokul Swamy, et al. ∙

research

∙ 03/01/2021

Information Discrepancy in Strategic Learning

We study the effects of information discrepancy across sub-populations o...

0 Yahav Bechavod, et al. ∙

research

∙ 02/21/2021

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

As machine learning black boxes are increasingly being deployed in criti...

10 Sushant Agarwal, et al. ∙

research

∙ 02/17/2021

Leveraging Public Data for Practical Private Query Release

In many statistical problems, incorporating priors can significantly imp...

0 Terrance Liu, et al. ∙

Zhiwei Steven Wu

Featured Co-authors