arXiv subjects

Zhiwei Steven Wu

Publications and source records attributed to Zhiwei Steven Wu.

At least 73 records · Page 4Linked to original sources

arXiv2024

Differentially Private Bayesian Persuasion

The tension between persuasion and privacy preservation is common in real-world settings. Online platforms should protect the privacy of web users whose data they collect, even as they seek to disclose information about these data to selling advertising spaces. Similarly, hospitals may share patient data to attract research investments with the obligation to preserve patients' privacy. To deal with these issues, we develop a framework to study Bayesian persuasion under differential privacy constraints, where the sender must design an optimal signaling scheme for persuasion while guaranteeing the privacy of each agent's private information in the database. To understand how privacy constraints affect information disclosure, we explore two perspectives within Bayesian persuasion: one views the mechanism as releasing a posterior about the private data, while the other views it as sending an action recommendation. The posterior-based formulation helps consider privacy-utility tradeoffs, quantifying how the tightness of privacy constraints impacts the sender's optimal utility. For any instance in a common utility function family and a wide range of privacy levels, a significant constant utility gap can be found between any two of the three conditions: $ε$-differential privacy constraint, relaxation $(ε,δ)$-differential privacy constraint, and no privacy constraint. We further geometrically characterize optimal signaling schemes under different types of constraints ($ε$-differential privacy, $(ε,δ)$-differential privacy and Renyi differential privacy), all of which can be seen as finding concave hulls in constrained posterior regions. Meanwhile, by taking the action-based view of persuasion, we provide polynomial-time algorithms for computing optimal differentially private signaling schemes, as long as a mild homogeneous condition is met.

cs.GT↗

arXiv2024

The Virtues of Pessimism in Inverse Reinforcement Learning

Inverse Reinforcement Learning (IRL) is a powerful framework for learning complex behaviors from expert demonstrations. However, it traditionally requires repeatedly solving a computationally expensive reinforcement learning (RL) problem in its inner loop. It is desirable to reduce the exploration burden by leveraging expert demonstrations in the inner-loop RL. As an example, recent work resets the learner to expert states in order to inform the learner of high-reward expert states. However, such an approach is infeasible in the real world. In this work, we consider an alternative approach to speeding up the RL subroutine in IRL: \emph{pessimism}, i.e., staying close to the expert's data distribution, instantiated via the use of offline RL algorithms. We formalize a connection between offline RL and IRL, enabling us to use an arbitrary offline RL algorithm to improve the sample efficiency of IRL. We validate our theory experimentally by demonstrating a strong correlation between the efficacy of an offline RL algorithm and how well it works as part of an IRL procedure. By using a strong offline RL algorithm as part of an IRL procedure, we are able to find policies that match expert performance significantly more efficiently than the prior art.

cs.LG↗

arXiv2024

Inverse Reinforcement Learning without Reinforcement Learning

Inverse Reinforcement Learning (IRL) is a powerful set of techniques for imitation learning that aims to learn a reward function that rationalizes expert demonstrations. Unfortunately, traditional IRL methods suffer from a computational weakness: they require repeatedly solving a hard reinforcement learning (RL) problem as a subroutine. This is counter-intuitive from the viewpoint of reductions: we have reduced the easier problem of imitation learning to repeatedly solving the harder problem of RL. Another thread of work has proved that access to the side-information of the distribution of states where a strong policy spends time can dramatically reduce the sample and computational complexities of solving an RL problem. 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. In practice, we find that we are able to significantly speed up the prior art on continuous control tasks.

cs.LG↗

arXiv2023

Strategyproof Decision-Making in Panel Data Settings and Beyond

We consider the problem of decision-making using panel data, in which a decision-maker gets noisy, repeated measurements of multiple units (or agents). We consider a setup where there is a pre-intervention period, when the principal observes the outcomes of each unit, after which the principal uses these observations to assign a treatment to each unit. 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. The principal's goal is to design a strategyproof intervention policy, i.e. a policy that assigns units to their utility-maximizing interventions despite their potential strategizing. We first identify a necessary and sufficient condition under which a strategyproof intervention policy exists, and provide a strategyproof mechanism with a simple closed form when one does exist. Along the way, we prove impossibility results for strategic multiclass classification, which may be of independent interest. When there are two interventions, we establish that there always exists a strategyproof mechanism, and provide an algorithm for learning such a mechanism. For three or more interventions, we provide an algorithm for learning a strategyproof mechanism if there exists a sufficiently large gap in the principal's rewards between different interventions. Finally, we empirically evaluate our model using real-world panel data collected from product sales over 18 months. We find that our methods compare favorably to baselines which do not take strategic interactions into consideration, even in the presence of model misspecification.

econ.EM↗

arXiv2023

Membership Inference Attacks on Diffusion Models via Quantile Regression

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 information about their training data. Here, we demonstrate a privacy vulnerability of diffusion models through a \emph{membership inference (MI) attack}, which aims to identify whether a target example belongs to the training set when given the trained diffusion model. Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training. This allows us to define a granular hypothesis test for determining the membership of a point in the training set, based on thresholding the reconstruction loss of that point using a custom threshold tailored to the example. We also provide a simple bootstrap technique that takes a majority membership prediction over ``a bag of weak attackers'' which improves the accuracy over individual quantile regression models. We show that our attack outperforms the prior state-of-the-art attack while being substantially less computationally expensive -- prior attacks required training multiple ``shadow models'' with the same architecture as the model under attack, whereas our attack requires training only much smaller models.

cs.LG↗

arXiv2023

Adaptive Privacy Composition for Accuracy-first Mechanisms

In many practical applications of differential privacy, practitioners seek to provide the best privacy guarantees subject to a target level of accuracy. A recent line of work by Ligett et al. '17 and Whitehouse et al. '22 has developed such accuracy-first mechanisms by leveraging the idea of noise reduction that adds correlated noise to the sufficient statistic in a private computation and produces a sequence of increasingly accurate answers. A major advantage of noise reduction mechanisms is that the analysts only pay the privacy cost of the least noisy or most accurate answer released. Despite this appealing property in isolation, there has not been a systematic study on how to use them in conjunction with other differentially private mechanisms. A fundamental challenge is that the privacy guarantee for noise reduction mechanisms is (necessarily) formulated as ex-post privacy that bounds the privacy loss as a function of the released outcome. Furthermore, there has yet to be any study on how ex-post private mechanisms compose, which allows us to track the accumulated privacy over several mechanisms. We develop privacy filters [Rogers et al. '16, Feldman and Zrnic '21, and Whitehouse et al. '22'] that allow an analyst to adaptively switch between differentially private and ex-post private mechanisms subject to an overall differential privacy guarantee.

cs.CR↗

arXiv2023

Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints

There is a disconnect between how researchers and practitioners handle privacy-utility tradeoffs. Researchers primarily operate from a privacy first perspective, setting strict privacy requirements and minimizing risk subject to these constraints. Practitioners often desire an accuracy first perspective, possibly satisfied with the greatest privacy they can get subject to obtaining sufficiently small error. Ligett et al. have introduced a "noise reduction" algorithm to address the latter perspective. The authors show that by adding correlated Laplace noise and progressively reducing it on demand, it is possible to produce a sequence of increasingly accurate estimates of a private parameter while only paying a privacy cost for the least noisy iterate released. In this work, we generalize noise reduction to the setting of Gaussian noise, introducing the Brownian mechanism. The Brownian mechanism works by first adding Gaussian noise of high variance corresponding to the final point of a simulated Brownian motion. Then, at the practitioner's discretion, noise is gradually decreased by tracing back along the Brownian path to an earlier time. Our mechanism is more naturally applicable to the common setting of bounded $\ell_2$-sensitivity, empirically outperforms existing work on common statistical tasks, and provides customizable control of privacy loss over the entire interaction with the practitioner. We complement our Brownian mechanism with ReducedAboveThreshold, a generalization of the classical AboveThreshold algorithm that provides adaptive privacy guarantees. Overall, our results demonstrate that one can meet utility constraints while still maintaining strong levels of privacy.

cs.LG↗

arXiv2023

Meta-Learning Adversarial Bandit Algorithms

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. As the first to target the adversarial online-within-online partial-information setting, we design meta-algorithms that combine outer learners to simultaneously tune the initialization and other hyperparameters of an inner learner for two important cases: multi-armed bandits (MAB) and bandit linear optimization (BLO). For MAB, the meta-learners initialize and set hyperparameters of the Tsallis-entropy generalization of Exp3, with the task-averaged regret improving if the entropy of the optima-in-hindsight is small. For BLO, we learn to initialize and tune online mirror descent (OMD) with self-concordant barrier regularizers, showing that task-averaged regret varies directly with an action space-dependent measure they induce. Our guarantees rely on proving that unregularized follow-the-leader combined with two levels of low-dimensional hyperparameter tuning is enough to learn a sequence of affine functions of non-Lipschitz and sometimes non-convex Bregman divergences bounding the regret of OMD.

cs.LG↗

arXiv2023

Strategic Apple Tasting

Algorithmic decision-making in high-stakes domains often involves assigning decisions to agents with incentives to strategically modify their input to the algorithm. In addition to dealing with incentives, in many domains of interest (e.g. lending and hiring) the decision-maker only observes feedback regarding their policy for rounds in which they assign a positive decision to the agent; this type of feedback is often referred to as apple tasting (or one-sided) feedback. We formalize this setting as an online learning problem with apple-tasting feedback where a principal makes decisions about a sequence of $T$ agents, each of which is represented by a context that may be strategically modified. Our goal is to achieve sublinear strategic regret, which compares the performance of the principal to that of the best fixed policy in hindsight, if the agents were truthful when revealing their contexts. Our main result is a learning algorithm which incurs $O (\sqrt{T})$ strategic regret when the sequence of agents is chosen stochastically. We also give an algorithm capable of handling adversarially-chosen agents, albeit at the cost of $O(T^{(d+1)/(d+2)})$ strategic regret (where $d$ is the dimension of the context). Our algorithms can be easily adapted to the setting where the principal receives bandit feedback -- this setting generalizes both the linear contextual bandit problem (by considering agents with incentives) and the strategic classification problem (by allowing for partial feedback).

cs.GT↗

arXiv2023

Fully Adaptive Composition in Differential Privacy

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 composition would permit. However, these results require that the privacy parameters of all algorithms be fixed before interacting with the data. To address this, Rogers et al. introduced fully adaptive composition, wherein both algorithms and their privacy parameters can be selected adaptively. They defined two probabilistic objects to measure privacy in adaptive composition: privacy filters, which provide differential privacy guarantees for composed interactions, and privacy odometers, time-uniform bounds on privacy loss. There are substantial gaps between advanced composition and existing filters and odometers. First, existing filters place stronger assumptions on the algorithms being composed. Second, these odometers and filters suffer from large constants, making them impractical. We construct filters that match the rates of advanced composition, including constants, despite allowing for adaptively chosen privacy parameters. En route we also derive a privacy filter for approximate zCDP. We also construct several general families of odometers. These odometers match the tightness of advanced composition at an arbitrary, preselected point in time, or at all points in time simultaneously, up to a doubly-logarithmic factor. We obtain our results by leveraging advances in martingale concentration. In sum, we show that fully adaptive privacy is obtainable at almost no loss.

cs.LG↗

arXiv2023

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

Many problems in machine learning rely on multi-task learning (MTL), in which the goal is to solve multiple related machine learning tasks simultaneously. MTL is particularly relevant for privacy-sensitive applications in areas such as healthcare, finance, and IoT computing, where sensitive data from multiple, varied sources are shared for the purpose of learning. In this work, we formalize notions of client-level privacy for MTL via joint differential privacy (JDP), a relaxation of differential privacy for mechanism design and distributed optimization. We then propose an algorithm for mean-regularized MTL, an objective commonly used for applications in personalized federated learning, subject to JDP. We analyze our objective and solver, providing certifiable guarantees on both privacy and utility. Empirically, we find that our method provides improved privacy/utility trade-offs relative to global baselines across common federated learning benchmarks.

cs.LG↗

arXiv2023

Learning Shared Safety Constraints from Multi-task Demonstrations

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. For example, regardless of whether it is making a sandwich or clearing the table, a kitchen robot should not break a plate. Manually specifying such a constraint can be both time-consuming and error-prone. We show how to learn constraints from expert demonstrations of safe task completion by extending inverse reinforcement learning (IRL) techniques to the space of constraints. Intuitively, we learn constraints that forbid highly rewarding behavior that the expert could have taken but chose not to. Unfortunately, the constraint learning problem is rather ill-posed and typically leads to overly conservative constraints that forbid all behavior that the expert did not take. We counter this by leveraging diverse demonstrations that naturally occur in multi-task settings to learn a tighter set of constraints. We validate our method with simulation experiments on high-dimensional continuous control tasks.

cs.LG↗

arXiv2023

On the Sublinear Regret of GP-UCB

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 sequentially chosen points. In particular, the learner aims to minimize regret, which is a measure of the suboptimality of the choices made. Arguably the most popular algorithm is the Gaussian Process Upper Confidence Bound (GP-UCB) algorithm, which involves acting based on a simple linear estimator of the unknown function. Despite its popularity, existing analyses of GP-UCB give a suboptimal regret rate, which fails to be sublinear for many commonly used kernels such as the Matérn kernel. This has led to a longstanding open question: are existing regret analyses for GP-UCB tight, or can bounds be improved by using more sophisticated analytical techniques? In this work, we resolve this open question and show that GP-UCB enjoys nearly optimal regret. In particular, our results yield sublinear regret rates for the Matérn kernel, improving over the state-of-the-art analyses and partially resolving a COLT open problem posed by Vakili et al. Our improvements rely on a key technical contribution -- regularizing kernel ridge estimators in proportion to the smoothness of the underlying kernel $k$. Applying this key idea together with a largely overlooked concentration result in separable Hilbert spaces (for which we provide an independent, simplified derivation), we are able to provide a tighter analysis of the GP-UCB algorithm.

cs.LG↗

arXiv2023

Private Data Stream Analysis for Universal Symmetric Norm Estimation

We study how to release summary statistics on a data stream subject to the constraint of differential privacy. In particular, we focus on releasing the family of symmetric norms, which are invariant under sign-flips and coordinate-wise permutations on an input data stream and include $L_p$ norms, $k$-support norms, top-$k$ norms, and the box norm as special cases. Although it may be possible to design and analyze a separate mechanism for each symmetric norm, we propose a general parametrizable framework that differentially privately releases a number of sufficient statistics from which the approximation of all symmetric norms can be simultaneously computed. Our framework partitions the coordinates of the underlying frequency vector into different levels based on their magnitude and releases approximate frequencies for the "heavy" coordinates in important levels and releases approximate level sizes for the "light" coordinates in important levels. Surprisingly, our mechanism allows for the release of an arbitrary number of symmetric norm approximations without any overhead or additional loss in privacy. Moreover, our mechanism permits $(1+α)$-approximation to each of the symmetric norms and can be implemented using sublinear space in the streaming model for many regimes of the accuracy and privacy parameters.

cs.DS↗

arXiv2023

Scalable Membership Inference Attacks via Quantile Regression

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 be formalized as a hypothesis testing problem. The most effective existing attacks estimate the distribution of some test statistic (usually the model's confidence on the true label) on points that were (and were not) used in training by training many \emph{shadow models} -- i.e. models of the same architecture as the model being attacked, trained on a random subsample of data. While effective, these attacks are extremely computationally expensive, especially when the model under attack is large. We introduce a new class of attacks based on performing quantile regression on the distribution of confidence scores induced by the model under attack on points that are not used in training. We show that our method is competitive with state-of-the-art shadow model attacks, while requiring substantially less compute because our attack requires training only a single model. Moreover, unlike shadow model attacks, our proposed attack does not require any knowledge of the architecture of the model under attack and is therefore truly ``black-box". We show the efficacy of this approach in an extensive series of experiments on various datasets and model architectures.

cs.LG↗

arXiv2023

Generating Private Synthetic Data with Genetic Algorithms

We study the problem of efficiently generating differentially private synthetic data that approximate the statistical properties of an underlying sensitive dataset. In recent years, there has been a growing line of work that approaches this problem using first-order optimization techniques. However, such techniques are restricted to optimizing differentiable objectives only, severely limiting the types of analyses that can be conducted. For example, first-order mechanisms have been primarily successful in approximating statistical queries only in the form of marginals for discrete data domains. In some cases, one can circumvent such issues by relaxing the task's objective to maintain differentiability. However, even when possible, these approaches impose a fundamental limitation in which modifications to the minimization problem become additional sources of error. Therefore, we propose Private-GSD, a private genetic algorithm based on zeroth-order optimization heuristics that do not require modifying the original objective. As a result, it avoids the aforementioned limitations of first-order optimization. We empirically evaluate Private-GSD against baseline algorithms on data derived from the American Community Survey across a variety of statistics--otherwise known as statistical queries--both for discrete and real-valued attributes. We show that Private-GSD outperforms the state-of-the-art methods on non-differential queries while matching accuracy in approximating differentiable ones.

cs.NE↗

arXiv2023

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

A growing literature on human-AI decision-making investigates strategies for combining human judgment with statistical models to improve decision-making. Research in this area often evaluates proposed improvements to models, interfaces, or workflows by demonstrating improved predictive performance on "ground truth" labels. However, this practice overlooks a key difference between human judgments and model predictions. Whereas humans reason about broader phenomena of interest in a decision -- including latent constructs that are not directly observable, such as disease status, the "toxicity" of online comments, or future "job performance" -- predictive models target proxy labels that are readily available in existing datasets. Predictive models' reliance on simplistic proxies makes them vulnerable to various sources of statistical bias. 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. We develop a causal framework to disentangle the relationship between each bias and clarify which are of concern in specific human-AI decision-making tasks. We demonstrate how our framework can be used to articulate implicit assumptions made in prior modeling work, and we recommend evaluation strategies for verifying whether these assumptions hold in practice. We then leverage our framework to re-examine the designs of prior human subjects experiments that investigate human-AI decision-making, finding that only a small fraction of studies examine factors related to target variable bias. We conclude by discussing opportunities to better address target variable bias in future research.

cs.CY↗

arXiv2023

Improved Differentially Private Regression via Gradient Boosting

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 -- including the ``clipping threshold'' that cannot be set optimally in a data-independent way. We give a new algorithm for private linear regression based on gradient boosting. We show that our method consistently improves over the previous state of the art when the clipping threshold is taken to be fixed without knowledge of the data, rather than optimized in a non-private way -- and that even when we optimize the hyperparameters of competitor algorithms non-privately, our algorithm is no worse and often better. In addition to a comprehensive set of experiments, we give theoretical insights to explain this behavior.

cs.LG↗