Search Results for author:
Found 89 papers, 30 papers with code
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
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.
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.
Inverse Reinforcement Learning without Reinforcement Learning
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.
Improved Differentially Private Regression via Gradient Boosting
We revisit the problem of differentially private squared error linear regression.
Choosing Public Datasets for Private Machine Learning via Gradient Subspace Distance
We give an algorithm for selecting a public dataset by measuring a low-dimensional subspace distance between gradients of the public and private examples.
Counterfactual Prediction Under Outcome Measurement Error
We also develop a method for estimating treatment-dependent measurement error parameters when these are unknown in advance.
Federated Learning as a Network Effects Game
Federated Learning (FL) aims to foster collaboration among a population of clients to improve the accuracy of machine learning without directly sharing local data.
Ground(less) Truth: A Causal Framework for Proxy Labels in Human-Algorithm Decision-Making
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.
Strategyproof Decision-Making in Panel Data Settings and Beyond
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.
Reinforcement Learning with Stepwise Fairness Constraints
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.
Confidence-Ranked Reconstruction of Census Microdata from Published Statistics
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.
Private Synthetic Data for Multitask Learning and Marginal Queries
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}.
Game-Theoretic Algorithms for Conditional Moment Matching
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).
Sequence Model Imitation Learning with Unobserved Contexts
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.
On Privacy and Personalization in Cross-Silo Federated Learning
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.
Brownian Noise Reduction: Maximizing Privacy Subject to Accuracy Constraints
In this work, we generalize noise reduction to the setting of Gaussian noise, introducing the Brownian mechanism.
Private Synthetic Data with Hierarchical Structure
Moreover, it has not yet been established how one can generate synthetic data at both the group and individual-level while capturing such statistics.
Incentivizing Combinatorial Bandit Exploration
The users are free to choose other actions and need to be incentivized to follow the algorithm's recommendations.
Minimax Optimal Online Imitation Learning via Replay Estimation
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.
Meta-Learning Adversarial Bandits
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.
Imagining new futures beyond predictive systems in child welfare: A qualitative study with impacted stakeholders
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.
Exploring How Machine Learning Practitioners (Try To) Use Fairness Toolkits
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.
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 human decision-making in high-stakes, social contexts.
Fair Federated Learning via Bounded Group Loss
In particular, we explore and extend the notion of Bounded Group Loss as a theoretically-grounded approach for group fairness.
Fully Adaptive Composition in Differential Privacy
However, these results require that the privacy parameters of all algorithms be fixed before interacting with the data.
Nonparametric extensions of randomized response for private confidence sets
This work derives methods for performing nonparametric, nonasymptotic statistical inference for population means under the constraint of local differential privacy (LDP).
Personalization Improves Privacy-Accuracy Tradeoffs in Federated Learning
Large-scale machine learning systems often involve data distributed across a collection of users.
Improved Regret for Differentially Private Exploration in Linear MDP
We study privacy-preserving exploration in sequential decision-making for environments that rely on sensitive data such as medical records.
Causal Imitation Learning under Temporally Correlated Noise
We develop algorithms for imitation learning from policy data that was corrupted by temporally correlated noise in expert actions.
Constrained Variational Policy Optimization for Safe Reinforcement Learning
Safe reinforcement learning (RL) aims to learn policies that satisfy certain constraints before deploying them to safety-critical applications.
Bayesian Persuasion for Algorithmic Recourse
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.
A Critique of Strictly Batch Imitation Learning
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.
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.
Incentivizing Compliance with Algorithmic Instruments
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.
Strategic Instrumental Variable Regression: Recovering Causal Relationships From Strategic Responses
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.
Understanding Clipping for Federated Learning: Convergence and Client-Level Differential Privacy
Recently, there has been a line of work on incorporating the formal privacy notion of differential privacy with FL.
Iterative Methods for Private Synthetic Data: Unifying Framework and New Methods
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.
Stateful Strategic Regression
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.
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap
We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching.
Information Discrepancy in Strategic Learning
We initiate the study of the effects of non-transparency in decision rules on individuals' ability to improve in strategic learning settings.
Towards the Unification and Robustness of Perturbation and Gradient Based Explanations
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.
Leveraging Public Data for Practical Private Query Release
In many statistical problems, incorporating priors can significantly improve performance.
Value Cards: An Educational Toolkit for Teaching Social Impacts of Machine Learning through Deliberation
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.
Private Reinforcement Learning with PAC and Regret Guarantees
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).
Bandit Data-Driven Optimization
In this paper, we introduce bandit data-driven optimization, the first iterative prediction-prescription framework to address these pain points.
Private Post-GAN Boosting
We also provide a non-private variant of PGB that improves the data quality of standard GAN training.
Competing Bandits: The Perils of Exploration Under Competition
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.
New Oracle-Efficient Algorithms for Private Synthetic Data Release
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.
Bypassing the Ambient Dimension: Private SGD with Gradient Subspace Identification
Existing lower bounds on private ERM show that such dependence on $p$ is inevitable in the worst case.
Understanding Gradient Clipping in Private SGD: A Geometric Perspective
Deep learning models are increasingly popular in many machine learning applications where the training data may contain sensitive information.
Private Stochastic Non-Convex Optimization: Adaptive Algorithms and Tighter Generalization Bounds
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.
Greedy Algorithm almost Dominates in Smoothed Contextual Bandits
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.
Private Query Release Assisted by Public Data
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.
Structured Linear Contextual Bandits: A Sharp and Geometric Smoothed Analysis
Bandit learning algorithms typically involve the balance of exploration and exploitation.
Privately Learning Markov Random Fields
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
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.
Gaming Helps! Learning from Strategic Interactions in Natural Dynamics
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.
Metric-Free Individual Fairness in Online Learning
We study an online learning problem subject to the constraint of individual fairness, which requires that similar individuals are treated similarly.
Learn to Expect the Unexpected: Probably Approximately Correct Domain Generalization
Domain generalization is the problem of machine learning when the training data and the test data come from different data domains.
Random Quadratic Forms with Dependence: Applications to Restricted Isometry and Beyond
We also discuss stochastic process based forms of J-L, RIP, and sketching, to illustrate the generality of the results.
Oracle Efficient Private Non-Convex Optimization
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.
Distributed Training with Heterogeneous Data: Bridging Median- and Mean-Based Algorithms
We show that these algorithms are non-convergent whenever there is some disparity between the expected median and mean over the local gradients.
Private Hypothesis Selection
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.
Fair Regression: Quantitative Definitions and Reduction-based Algorithms
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.
An Algorithmic Framework for Fairness Elicitation
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.
Bayesian Exploration with Heterogeneous Agents
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.
The Perils of Exploration under Competition: A Computational Modeling Approach
We empirically study the interplay between exploration and competition.
Equal Opportunity in Online Classification with Partial Feedback
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.
Privacy-Preserving Distributed Deep Learning for Clinical Data
Deep learning with medical data often requires larger samples sizes than are available at single providers.
Locally Private Gaussian Estimation
We study a basic private estimation problem: each of $n$ users draws a single i. i. d.
How to Use Heuristics for Differential Privacy
We show that there is an efficient algorithm for privately constructing synthetic data for any such class, given a non-private learning oracle.
Incentivizing Exploration with Selective Data Disclosure
We propose and design recommendation systems that incentivize efficient exploration.
An Empirical Study of Rich Subgroup Fairness for Machine Learning
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.
Orthogonal Random Forest for Causal Inference
We provide a consistency rate and establish asymptotic normality for our estimator.
The Externalities of Exploration and How Data Diversity Helps Exploitation
Returning to group-level effects, we show that under the same conditions, negative group externalities essentially vanish under the greedy algorithm.
Locally Private Bayesian Inference for Count Models
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.
Semiparametric Contextual Bandits
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.
A Smoothed Analysis of the Greedy Algorithm for the Linear Contextual Bandit Problem
Bandit learning is characterized by the tension between long-term exploration and short-term exploitation.
Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
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.
Strategic Classification from Revealed Preferences
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.
Meritocratic Fairness for Cross-Population Selection
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.
Competing Bandits: Learning under Competition
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.
Multidimensional Dynamic Pricing for Welfare Maximization
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
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 $y$.
Adaptive Learning with Robust Generalization Guarantees
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.
Bayesian Exploration: Incentivizing Exploration in Bayesian Games
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
This models the problem of predicting the behavior of a rational agent whose goals are known, but whose resources are unknown.
Watch and Learn: Optimizing from Revealed Preferences Feedback
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.
Dual Query: Practical Private Query Release for High Dimensional Data
We present a practical, differentially private algorithm for answering a large number of queries on high dimensional datasets.
