Search Results for author: Zhiwei Steven Wu

Found 99 papers, 32 papers with code

Orthogonal Random Forest for Causal Inference

1 code implementation9 Jun 2018 Miruna Oprescu, Vasilis Syrgkanis, Zhiwei Steven Wu

We provide a consistency rate and establish asymptotic normality for our estimator.

Causal Inference

Fair Regression: Quantitative Definitions and Reduction-based Algorithms

4 code implementations30 May 2019 Alekh Agarwal, Miroslav Dudík, Zhiwei Steven Wu

Our schemes only require access to standard risk minimization algorithms (such as standard classification or least-squares regression) while providing theoretical guarantees on the optimality and fairness of the obtained solutions.

Attribute Fairness +1

Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap

2 code implementations4 Mar 2021 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching.

Imitation Learning

Constrained Variational Policy Optimization for Safe Reinforcement Learning

2 code implementations28 Jan 2022 Zuxin Liu, Zhepeng Cen, Vladislav Isenbaev, Wei Liu, Zhiwei Steven Wu, Bo Li, Ding Zhao

Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.

reinforcement-learning Reinforcement Learning (RL) +1

Inverse Reinforcement Learning without Reinforcement Learning

1 code implementation26 Mar 2023 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

In this work, we demonstrate for the first time a more informed imitation learning reduction where we utilize the state distribution of the expert to alleviate the global exploration component of the RL subroutine, providing an exponential speedup in theory.

Continuous Control Imitation Learning +2

Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness

5 code implementations ICML 2018 Michael Kearns, Seth Neel, Aaron Roth, Zhiwei Steven Wu

We prove that the computational problem of auditing subgroup fairness for both equality of false positive rates and statistical parity is equivalent to the problem of weak agnostic learning, which means it is computationally hard in the worst case, even for simple structured subclasses.

Fairness

An Empirical Study of Rich Subgroup Fairness for Machine Learning

5 code implementations24 Aug 2018 Michael Kearns, Seth Neel, Aaron Roth, Zhiwei Steven Wu

In this paper, we undertake an extensive empirical evaluation of the algorithm of Kearns et al. On four real datasets for which fairness is a concern, we investigate the basic convergence of the algorithm when instantiated with fast heuristics in place of learning oracles, measure the tradeoffs between fairness and accuracy, and compare this approach with the recent algorithm of Agarwal et al. [2018], which implements weaker and more traditional marginal fairness constraints defined by individual protected attributes.

BIG-bench Machine Learning Fairness

Semiparametric Contextual Bandits

2 code implementations ICML 2018 Akshay Krishnamurthy, Zhiwei Steven Wu, Vasilis Syrgkanis

This paper studies semiparametric contextual bandits, a generalization of the linear stochastic bandit problem where the reward for an action is modeled as a linear function of known action features confounded by an non-linear action-independent term.

Multi-Armed Bandits

On Privacy and Personalization in Cross-Silo Federated Learning

1 code implementation16 Jun 2022 Ziyu Liu, Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith

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 cross-silo FL, a setting characterized by a limited number of clients each containing many data subjects.

Federated Learning Multi-Task Learning

Confidence-Ranked Reconstruction of Census Microdata from Published Statistics

1 code implementation6 Nov 2022 Travis Dick, Cynthia Dwork, Michael Kearns, Terrance Liu, Aaron Roth, Giuseppe Vietri, Zhiwei Steven Wu

Our attacks significantly outperform those that are based only on access to a public distribution or population from which the private dataset $D$ was sampled, demonstrating that they are exploiting information in the aggregate statistics $Q(D)$, and not simply the overall structure of the distribution.

Reconstruction Attack

Private Post-GAN Boosting

1 code implementation ICLR 2021 Marcel Neunhoeffer, Zhiwei Steven Wu, Cynthia Dwork

We also provide a non-private variant of PGB that improves the data quality of standard GAN training.

New Oracle-Efficient Algorithms for Private Synthetic Data Release

1 code implementation ICML 2020 Giuseppe Vietri, Grace Tian, Mark Bun, Thomas Steinke, Zhiwei Steven Wu

We present three new algorithms for constructing differentially private synthetic data---a sanitized version of a sensitive dataset that approximately preserves the answers to a large collection of statistical queries.

Causal Imitation Learning under Temporally Correlated Noise

1 code implementation2 Feb 2022 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

We develop algorithms for imitation learning from policy data that was corrupted by temporally correlated noise in expert actions.

Econometrics Imitation Learning

Locally Private Bayesian Inference for Count Models

1 code implementation22 Mar 2018 Aaron Schein, Zhiwei Steven Wu, Alexandra Schofield, Mingyuan Zhou, Hanna Wallach

We present a general method for privacy-preserving Bayesian inference in Poisson factorization, a broad class of models that includes some of the most widely used models in the social sciences.

Bayesian Inference Link Prediction +1

Sequence Model Imitation Learning with Unobserved Contexts

1 code implementation3 Aug 2022 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

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.

Continuous Control Imitation Learning

Oracle Efficient Private Non-Convex Optimization

1 code implementation ICML 2020 Seth Neel, Aaron Roth, Giuseppe Vietri, Zhiwei Steven Wu

We find that for the problem of learning linear classifiers, directly optimizing for 0/1 loss using our approach can out-perform the more standard approach of privately optimizing a convex-surrogate loss function on the Adult dataset.

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

1 code implementation NeurIPS 2021 Terrance Liu, Giuseppe Vietri, Zhiwei Steven Wu

We study private synthetic data generation for query release, where the goal is to construct a sanitized version of a sensitive dataset, subject to differential privacy, that approximately preserves the answers to a large collection of statistical queries.

Synthetic Data Generation

Learning Shared Safety Constraints from Multi-task Demonstrations

1 code implementation NeurIPS 2023 Konwoo Kim, Gokul Swamy, Zuxin Liu, Ding Zhao, Sanjiban Choudhury, Zhiwei Steven Wu

Regardless of the particular task we want them to perform in an environment, there are often shared safety constraints we want our agents to respect.

Continuous Control

Bandit Data-Driven Optimization

1 code implementation26 Aug 2020 Zheyuan Ryan Shi, Zhiwei Steven Wu, Rayid Ghani, Fei Fang

In this paper, we introduce bandit data-driven optimization, the first iterative prediction-prescription framework to address these pain points.

BIG-bench Machine Learning

Leveraging Public Data for Practical Private Query Release

1 code implementation17 Feb 2021 Terrance Liu, Giuseppe Vietri, Thomas Steinke, Jonathan Ullman, Zhiwei Steven Wu

In many statistical problems, incorporating priors can significantly improve performance.

Generating Private Synthetic Data with Genetic Algorithms

1 code implementation5 Jun 2023 Terrance Liu, Jingwu Tang, Giuseppe Vietri, Zhiwei Steven Wu

We study the problem of efficiently generating differentially private synthetic data that approximate the statistical properties of an underlying sensitive dataset.

An Algorithmic Framework for Fairness Elicitation

1 code implementation25 May 2019 Christopher Jung, Michael Kearns, Seth Neel, Aaron Roth, Logan Stapleton, Zhiwei Steven Wu

We consider settings in which the right notion of fairness is not captured by simple mathematical definitions (such as equality of error rates across groups), but might be more complex and nuanced and thus require elicitation from individual or collective stakeholders.

Fairness Generalization Bounds

Minimax Optimal Online Imitation Learning via Replay Estimation

1 code implementation30 May 2022 Gokul Swamy, Nived Rajaraman, Matthew Peng, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu, Jiantao Jiao, Kannan Ramchandran

In the tabular setting or with linear function approximation, our meta theorem shows that the performance gap incurred by our approach achieves the optimal $\widetilde{O} \left( \min({H^{3/2}} / {N}, {H} / {\sqrt{N}} \right)$ dependency, under significantly weaker assumptions compared to prior work.

Continuous Control Imitation Learning

Counterfactual Prediction Under Outcome Measurement Error

1 code implementation22 Feb 2023 Luke Guerdan, Amanda Coston, Kenneth Holstein, Zhiwei Steven Wu

We also develop a method for estimating treatment-dependent measurement error parameters when these are unknown in advance.

counterfactual Decision Making +1

Hybrid Inverse Reinforcement Learning

1 code implementation13 Feb 2024 Juntao Ren, Gokul Swamy, Zhiwei Steven Wu, J. Andrew Bagnell, Sanjiban Choudhury

In this work, we propose using hybrid RL -- training on a mixture of online and expert data -- to curtail unnecessary exploration.

Continuous Control Imitation Learning +2

The Externalities of Exploration and How Data Diversity Helps Exploitation

no code implementations1 Jun 2018 Manish Raghavan, Aleksandrs Slivkins, Jennifer Wortman Vaughan, Zhiwei Steven Wu

Returning to group-level effects, we show that under the same conditions, negative group externalities essentially vanish under the greedy algorithm.

Multi-Armed Bandits

Competing Bandits: Learning under Competition

no code implementations27 Feb 2017 Yishay Mansour, Aleksandrs Slivkins, Zhiwei Steven Wu

Most modern systems strive to learn from interactions with users, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information.

Strategic Classification from Revealed Preferences

no code implementations22 Oct 2017 Jinshuo Dong, Aaron Roth, Zachary Schutzman, Bo Waggoner, Zhiwei Steven Wu

We study an online linear classification problem, in which the data is generated by strategic agents who manipulate their features in an effort to change the classification outcome.

Classification General Classification

Multidimensional Dynamic Pricing for Welfare Maximization

no code implementations19 Jul 2016 Aaron Roth, Aleksandrs Slivkins, Jonathan Ullman, Zhiwei Steven Wu

We are able to apply this technique to the setting of unit demand buyers despite the fact that in that setting the goods are not divisible, and the natural fractional relaxation of a unit demand valuation is not strongly concave.

Predicting with Distributions

no code implementations3 Jun 2016 Michael Kearns, Zhiwei Steven Wu

We consider a new learning model in which a joint distribution over vector pairs $(x, y)$ is determined by an unknown function $c(x)$ that maps input vectors $x$ not to individual outputs, but to entire {\em distributions\/} over output vectors $y$.

General Classification PAC learning

Bayesian Exploration: Incentivizing Exploration in Bayesian Games

no code implementations24 Feb 2016 Yishay Mansour, Aleksandrs Slivkins, Vasilis Syrgkanis, Zhiwei Steven Wu

As a key technical tool, we introduce the concept of explorable actions, the actions which some incentive-compatible policy can recommend with non-zero probability.

Learning from Rational Behavior: Predicting Solutions to Unknown Linear Programs

no code implementations NeurIPS 2016 Shahin Jabbari, Ryan Rogers, Aaron Roth, Zhiwei Steven Wu

This models the problem of predicting the behavior of a rational agent whose goals are known, but whose resources are unknown.

Adaptive Learning with Robust Generalization Guarantees

no code implementations24 Feb 2016 Rachel Cummings, Katrina Ligett, Kobbi Nissim, Aaron Roth, Zhiwei Steven Wu

We also show that perfect generalization is a strictly stronger guarantee than differential privacy, but that, nevertheless, many learning tasks can be carried out subject to the guarantees of perfect generalization.

Dual Query: Practical Private Query Release for High Dimensional Data

no code implementations6 Feb 2014 Marco Gaboardi, Emilio Jesús Gallego Arias, Justin Hsu, Aaron Roth, Zhiwei Steven Wu

We present a practical, differentially private algorithm for answering a large number of queries on high dimensional datasets.

Vocal Bursts Intensity Prediction

Watch and Learn: Optimizing from Revealed Preferences Feedback

no code implementations4 Apr 2015 Aaron Roth, Jonathan Ullman, Zhiwei Steven Wu

In this paper we present an approach to solving for the leader's optimal strategy in certain Stackelberg games where the follower's utility function (and thus the subsequent best response of the follower) is unknown.

How to Use Heuristics for Differential Privacy

no code implementations19 Nov 2018 Seth Neel, Aaron Roth, Zhiwei Steven Wu

We show that there is an efficient algorithm for privately constructing synthetic data for any such class, given a non-private learning oracle.

PAC learning

Locally Private Gaussian Estimation

no code implementations NeurIPS 2019 Matthew Joseph, Janardhan Kulkarni, Jieming Mao, Zhiwei Steven Wu

We study a basic private estimation problem: each of $n$ users draws a single i. i. d.

Privacy-Preserving Distributed Deep Learning for Clinical Data

no code implementations4 Dec 2018 Brett K. Beaulieu-Jones, William Yuan, Samuel G. Finlayson, Zhiwei Steven Wu

Deep learning with medical data often requires larger samples sizes than are available at single providers.

Privacy Preserving

Meritocratic Fairness for Cross-Population Selection

no code implementations ICML 2017 Michael Kearns, Aaron Roth, Zhiwei Steven Wu

We consider the problem of selecting a strong pool of individuals from several populations with incomparable skills (e. g. soccer players, mathematicians, and singers) in a fair manner.

Fairness

Equal Opportunity in Online Classification with Partial Feedback

1 code implementation NeurIPS 2019 Yahav Bechavod, Katrina Ligett, Aaron Roth, Bo Waggoner, Zhiwei Steven Wu

We study an online classification problem with partial feedback in which individuals arrive one at a time from a fixed but unknown distribution, and must be classified as positive or negative.

Classification Decision Making Under Uncertainty +3

Bayesian Exploration with Heterogeneous Agents

no code implementations19 Feb 2019 Nicole Immorlica, Jieming Mao, Aleksandrs Slivkins, Zhiwei Steven Wu

We consider Bayesian Exploration: a simple model in which the recommendation system (the "principal") controls the information flow to the users (the "agents") and strives to incentivize exploration via information asymmetry.

Recommendation Systems

Private Hypothesis Selection

no code implementations NeurIPS 2019 Mark Bun, Gautam Kamath, Thomas Steinke, Zhiwei Steven Wu

The sample complexity of our basic algorithm is $O\left(\frac{\log m}{\alpha^2} + \frac{\log m}{\alpha \varepsilon}\right)$, representing a minimal cost for privacy when compared to the non-private algorithm.

PAC learning

Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms

no code implementations NeurIPS 2020 Xiangyi Chen, Tiancong Chen, Haoran Sun, Zhiwei Steven Wu, Mingyi Hong

We show that these algorithms are non-convergent whenever there is some disparity between the expected median and mean over the local gradients.

Federated Learning

Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization

no code implementations13 Feb 2020 Vikas K. Garg, Adam Kalai, Katrina Ligett, Zhiwei Steven Wu

Domain generalization is the problem of machine learning when the training data and the test data come from different data domains.

Domain Generalization feature selection

Metric-Free Individual Fairness in Online Learning

no code implementations NeurIPS 2020 Yahav Bechavod, Christopher Jung, Zhiwei Steven Wu

We study an online learning problem subject to the constraint of individual fairness, which requires that similar individuals are treated similarly.

Fairness General Classification +1

Gaming Helps! Learning from Strategic Interactions in Natural Dynamics

no code implementations17 Feb 2020 Yahav Bechavod, Katrina Ligett, Zhiwei Steven Wu, Juba Ziani

We consider an online regression setting in which individuals adapt to the regression model: arriving individuals are aware of the current model, and invest strategically in modifying their own features so as to improve the predicted score that the current model assigns to them.

Causal Discovery regression

Privately Learning Markov Random Fields

no code implementations ICML 2020 Huanyu Zhang, Gautam Kamath, Janardhan Kulkarni, Zhiwei Steven Wu

We consider the problem of learning Markov Random Fields (including the prototypical example, the Ising model) under the constraint of differential privacy.

Locally Private Hypothesis Selection

no code implementations21 Feb 2020 Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang

Absent privacy constraints, this problem requires $O(\log k)$ samples from $p$, and it was recently shown that the same complexity is achievable under (central) differential privacy.

Two-sample testing

Private Query Release Assisted by Public Data

no code implementations ICML 2020 Raef Bassily, Albert Cheu, Shay Moran, Aleksandar Nikolov, Jonathan Ullman, Zhiwei Steven Wu

In comparison, with only private samples, this problem cannot be solved even for simple query classes with VC-dimension one, and without any private samples, a larger public sample of size $d/\alpha^2$ is needed.

Greedy Algorithm almost Dominates in Smoothed Contextual Bandits

no code implementations19 May 2020 Manish Raghavan, Aleksandrs Slivkins, Jennifer Wortman Vaughan, Zhiwei Steven Wu

Online learning algorithms, widely used to power search and content optimization on the web, must balance exploration and exploitation, potentially sacrificing the experience of current users in order to gain information that will lead to better decisions in the future.

Multi-Armed Bandits

Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds

no code implementations24 Jun 2020 Yingxue Zhou, Xiangyi Chen, Mingyi Hong, Zhiwei Steven Wu, Arindam Banerjee

We obtain this rate by providing the first analyses on a collection of private gradient-based methods, including adaptive algorithms DP RMSProp and DP Adam.

Generalization Bounds

Understanding Gradient Clipping in Private SGD: A Geometric Perspective

no code implementations NeurIPS 2020 Xiangyi Chen, Zhiwei Steven Wu, Mingyi Hong

Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information.

Competing Bandits: The Perils of Exploration Under Competition

no code implementations20 Jul 2020 Guy Aridor, Yishay Mansour, Aleksandrs Slivkins, Zhiwei Steven Wu

Users arrive one by one and choose between the two firms, so that each firm makes progress on its bandit problem only if it is chosen.

Multi-Armed Bandits

Private Reinforcement Learning with PAC and Regret Guarantees

no code implementations18 Sep 2020 Giuseppe Vietri, Borja Balle, Akshay Krishnamurthy, Zhiwei Steven Wu

Motivated by high-stakes decision-making domains like personalized medicine where user information is inherently sensitive, we design privacy preserving exploration policies for episodic reinforcement learning (RL).

Decision Making Privacy Preserving +2

Value Cards: An Educational Toolkit for Teaching Social Impacts of Machine Learning through Deliberation

no code implementations22 Oct 2020 Hong Shen, Wesley Hanwen Deng, Aditi Chattopadhyay, Zhiwei Steven Wu, Xu Wang, Haiyi Zhu

In this paper, we present Value Card, an educational toolkit to inform students and practitioners of the social impacts of different machine learning models via deliberation.

BIG-bench Machine Learning Ethics +1

Towards the Unification and Robustness of Perturbation and Gradient Based Explanations

no code implementations21 Feb 2021 Sushant Agarwal, Shahin Jabbari, Chirag Agarwal, Sohini Upadhyay, Zhiwei Steven Wu, Himabindu Lakkaraju

As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner.

Information Discrepancy in Strategic Learning

no code implementations1 Mar 2021 Yahav Bechavod, Chara Podimata, Zhiwei Steven Wu, Juba Ziani

We initiate the study of the effects of non-transparency in decision rules on individuals' ability to improve in strategic learning settings.

Decision Making

Stateful Strategic Regression

no code implementations NeurIPS 2021 Keegan Harris, Hoda Heidari, Zhiwei Steven Wu

In particular, we consider settings in which the agent's effort investment today can accumulate over time in the form of an internal state - impacting both his future rewards and that of the principal.

Decision Making regression

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

no code implementations25 Jun 2021 Xinwei Zhang, Xiangyi Chen, Mingyi Hong, Zhiwei Steven Wu, JinFeng Yi

Recently, there has been a line of work on incorporating the formal privacy notion of differential privacy with FL.

Federated Learning

Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses

1 code implementation12 Jul 2021 Keegan Harris, Daniel Ngo, Logan Stapleton, Hoda Heidari, Zhiwei Steven Wu

In settings where Machine Learning (ML) algorithms automate or inform consequential decisions about people, individual decision subjects are often incentivized to strategically modify their observable attributes to receive more favorable predictions.

Decision Making Fairness +1

Incentivizing Compliance with Algorithmic Instruments

1 code implementation21 Jul 2021 Daniel Ngo, Logan Stapleton, Vasilis Syrgkanis, Zhiwei Steven Wu

In rounds, a social planner interacts with a sequence of heterogeneous agents who arrive with their unobserved private type that determines both their prior preferences across the actions (e. g., control and treatment) and their baseline rewards without taking any treatment.

Selection bias

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

1 code implementation30 Aug 2021 Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith

Many problems in machine learning rely on multi-task learning (MTL), in which the goal is to solve multiple related machine learning tasks simultaneously.

BIG-bench Machine Learning Distributed Optimization +2

A Critique of Strictly Batch Imitation Learning

no code implementations5 Oct 2021 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

Recent work by Jarrett et al. attempts to frame the problem of offline imitation learning (IL) as one of learning a joint energy-based model, with the hope of out-performing standard behavioral cloning.

Imitation Learning

Bayesian Persuasion for Algorithmic Recourse

no code implementations12 Dec 2021 Keegan Harris, Valerie Chen, Joon Sik Kim, Ameet Talwalkar, Hoda Heidari, Zhiwei Steven Wu

While the decision maker's problem of finding the optimal Bayesian incentive-compatible (BIC) signaling policy takes the form of optimization over infinitely-many variables, we show that this optimization can be cast as a linear program over finitely-many regions of the space of possible assessment rules.

Decision Making

Improved Regret for Differentially Private Exploration in Linear MDP

no code implementations2 Feb 2022 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.

Decision Making Privacy Preserving +1

Nonparametric extensions of randomized response for private confidence sets

1 code implementation17 Feb 2022 Ian Waudby-Smith, Zhiwei Steven Wu, Aaditya Ramdas

This work derives methods for performing nonparametric, nonasymptotic statistical inference for population means under the constraint of local differential privacy (LDP).

Fully Adaptive Composition in Differential Privacy

no code implementations10 Mar 2022 Justin Whitehouse, Aaditya Ramdas, Ryan Rogers, Zhiwei Steven Wu

However, these results require that the privacy parameters of all algorithms be fixed before interacting with the data.

Fair Federated Learning via Bounded Group Loss

no code implementations18 Mar 2022 Shengyuan Hu, Zhiwei Steven Wu, Virginia Smith

In particular, we explore and extend the notion of Bounded Group Loss as a theoretically-grounded approach for group fairness.

Fairness Federated Learning

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

no code implementations13 May 2022 Wesley Hanwen Deng, Manish Nagireddy, Michelle Seng Ah Lee, Jatinder Singh, Zhiwei Steven Wu, Kenneth Holstein, Haiyi Zhu

Recent years have seen the development of many open-source ML fairness toolkits aimed at helping ML practitioners assess and address unfairness in their systems.

BIG-bench Machine Learning Fairness

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

no code implementations18 May 2022 Logan Stapleton, Min Hun Lee, Diana Qing, Marya Wright, Alexandra Chouldechova, Kenneth Holstein, Zhiwei Steven Wu, Haiyi Zhu

In this work, we conducted a set of seven design workshops with 35 stakeholders who have been impacted by the child welfare system or who work in it to understand their beliefs and concerns around PRMs, and to engage them in imagining new uses of data and technologies in the child welfare system.

Decision Making

Meta-Learning Adversarial Bandits

no code implementations27 May 2022 Maria-Florina Balcan, Keegan Harris, Mikhail Khodak, Zhiwei Steven Wu

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-similarity measure.

Meta-Learning Multi-Armed Bandits

Incentivizing Combinatorial Bandit Exploration

no code implementations1 Jun 2022 Xinyan Hu, Dung Daniel Ngo, Aleksandrs Slivkins, Zhiwei Steven Wu

The users are free to choose other actions and need to be incentivized to follow the algorithm's recommendations.

Thompson Sampling

Private Synthetic Data with Hierarchical Structure

no code implementations13 Jun 2022 Terrance Liu, Zhiwei Steven Wu

Moreover, it has not yet been established how one can generate synthetic data at both the group and individual-level while capturing such statistics.

Synthetic Data Generation

Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints

no code implementations15 Jun 2022 Justin Whitehouse, Zhiwei Steven Wu, Aaditya Ramdas, Ryan Rogers

In this work, we generalize noise reduction to the setting of Gaussian noise, introducing the Brownian mechanism.

Game-Theoretic Algorithms for Conditional Moment Matching

no code implementations19 Aug 2022 Gokul Swamy, Sanjiban Choudhury, J. Andrew Bagnell, Zhiwei Steven Wu

A variety of problems in econometrics and machine learning, including instrumental variable regression and Bellman residual minimization, can be formulated as satisfying a set of conditional moment restrictions (CMR).

Econometrics regression

Private Synthetic Data for Multitask Learning and Marginal Queries

no code implementations15 Sep 2022 Giuseppe Vietri, Cedric Archambeau, Sergul Aydore, William Brown, Michael Kearns, Aaron Roth, Ankit Siva, Shuai Tang, Zhiwei Steven Wu

A key innovation in our algorithm is the ability to directly handle numerical features, in contrast to a number of related prior approaches which require numerical features to be first converted into {high cardinality} categorical features via {a binning strategy}.

Reinforcement Learning with Stepwise Fairness Constraints

no code implementations8 Nov 2022 Zhun Deng, He Sun, Zhiwei Steven Wu, Linjun Zhang, David C. Parkes

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.

Decision Making Fairness +2

Strategyproof Decision-Making in Panel Data Settings and Beyond

no code implementations25 Nov 2022 Keegan Harris, Anish Agarwal, Chara Podimata, Zhiwei Steven Wu

Unlike this classical setting, we permit the units generating the panel data to be strategic, i. e. units may modify their pre-intervention outcomes in order to receive a more desirable intervention.

Decision Making Econometrics

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

no code implementations13 Feb 2023 Luke Guerdan, Amanda Coston, Zhiwei Steven Wu, Kenneth Holstein

In this paper, we identify five sources of target variable bias that can impact the validity of proxy labels in human-AI decision-making tasks.

Decision Making

Federated Learning as a Network Effects Game

no code implementations16 Feb 2023 Shengyuan Hu, Dung Daniel Ngo, Shuran Zheng, Virginia Smith, Zhiwei Steven Wu

Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data.

Federated Learning

Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance

no code implementations2 Mar 2023 Xin Gu, Gautam Kamath, Zhiwei Steven Wu

We give an algorithm for selecting a public dataset by measuring a low-dimensional subspace distance between gradients of the public and private examples.

Adaptive Privacy Composition for Accuracy-first Mechanisms

no code implementations NeurIPS 2023 Ryan Rogers, Gennady Samorodnitsky, Zhiwei Steven Wu, Aaditya Ramdas

In many practical applications of differential privacy, practitioners seek to provide the best privacy guarantees subject to a target level of accuracy.

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach

no code implementations24 Nov 2023 Xinwei Zhang, Zhiqi Bu, Zhiwei Steven Wu, Mingyi Hong

In our work, we propose a new error-feedback (EF) DP algorithm as an alternative to DPSGD-GC, which not only offers a diminishing utility bound without inducing a constant clipping bias, but more importantly, it allows for an arbitrary choice of clipping threshold that is independent of the problem.

Membership Inference Attacks on Diffusion Models via Quantile Regression

no code implementations8 Dec 2023 Shuai Tang, Zhiwei Steven Wu, Sergul Aydore, Michael Kearns, Aaron Roth

Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training.

Image Generation regression

Leveraging Public Representations for Private Transfer Learning

no code implementations24 Dec 2023 Pratiksha Thaker, Amrith Setlur, Zhiwei Steven Wu, Virginia Smith

Motivated by the recent empirical success of incorporating public data into differentially private learning, we theoretically investigate how a shared representation learned from public data can improve private learning.

regression Transfer Learning

Incentive-Aware Synthetic Control: Accurate Counterfactual Estimation via Incentivized Exploration

no code implementations26 Dec 2023 Daniel Ngo, Keegan Harris, Anish Agarwal, Vasilis Syrgkanis, Zhiwei Steven Wu

We consider the setting of synthetic control methods (SCMs), a canonical approach used to estimate the treatment effect on the treated in a panel data setting.

counterfactual valid

A Minimaximalist Approach to Reinforcement Learning from Human Feedback

no code implementations8 Jan 2024 Gokul Swamy, Christoph Dann, Rahul Kidambi, Zhiwei Steven Wu, Alekh Agarwal

Our approach is maximalist in that it provably handles non-Markovian, intransitive, and stochastic preferences while being robust to the compounding errors that plague offline approaches to sequential prediction.

Continuous Control reinforcement-learning

The Virtues of Pessimism in Inverse Reinforcement Learning

no code implementations4 Feb 2024 David Wu, Gokul Swamy, J. Andrew Bagnell, Zhiwei Steven Wu, Sanjiban Choudhury

Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations.

Offline RL reinforcement-learning +1

Regret Minimization in Stackelberg Games with Side Information

no code implementations13 Feb 2024 Keegan Harris, Zhiwei Steven Wu, Maria-Florina Balcan

Stackelberg games are perhaps one of the biggest success stories of algorithmic game theory over the last decade, as algorithms for playing in Stackelberg games have been deployed in many real-world domains including airport security, anti-poaching efforts, and cyber-crime prevention.

Provable Multi-Party Reinforcement Learning with Diverse Human Feedback

no code implementations8 Mar 2024 Huiying Zhong, Zhun Deng, Weijie J. Su, Zhiwei Steven Wu, Linjun Zhang

Our work \textit{initiates} the theoretical study of multi-party RLHF that explicitly models the diverse preferences of multiple individuals.

Fairness Meta-Learning +1

Cannot find the paper you are looking for? You can Submit a new open access paper.