Automated decision-making tools increasingly assess individuals to determine if they qualify for high-stakes opportunities. A recent line of research investigates how strategic agents may respond to such scoring tools to receive favorable assessments. While prior work has focused on the short-term strategic interactions between a decision-making institution (modeled as a principal) and individual decision-subjects (modeled as agents), we investigate interactions spanning multiple time-steps. 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. We characterize the Stackelberg equilibrium of the resulting game and provide novel algorithms for computing it. Our analysis reveals several intriguing insights about the role of multiple interactions in shaping the game's outcome: First, we establish that in our stateful setting, the class of all linear assessment policies remains as powerful as the larger class of all monotonic assessment policies. While recovering the principal's optimal policy requires solving a non-convex optimization problem, we provide polynomial-time algorithms for recovering both the principal and agent's optimal policies under common assumptions about the process by which effort investments convert to observable features. Most importantly, we show that with multiple rounds of interaction at her disposal, the principal is more effective at incentivizing the agent to accumulate effort in her desired direction. Our work addresses several critical gaps in the growing literature on the societal impacts of automated decision-making - by focusing on longer time horizons and accounting for the compounding nature of decisions individuals receive over time.
We provide a unifying view of a large family of previous imitation learning algorithms through the lens of moment matching. At its core, our classification scheme is based on whether the learner attempts to match (1) reward or (2) action-value moments of the expert's behavior, with each option leading to differing algorithmic approaches. By considering adversarially chosen divergences between learner and expert behavior, we are able to derive bounds on policy performance that apply for all algorithms in each of these classes, the first to our knowledge. We also introduce the notion of recoverability, implicit in many previous analyses of imitation learning, which allows us to cleanly delineate how well each algorithmic family is able to mitigate compounding errors. We derive two novel algorithm templates, AdVIL and AdRIL, with strong guarantees, simple implementation, and competitive empirical performance.
We study a decision-making model where a principal deploys a scoring rule and the agents strategically invest effort to improve their scores. Unlike existing work in the strategic learning literature, we do not assume that the principal's scoring rule is fully known to the agents, and agents may form different estimates of the scoring rule based on their own sources of information. We focus on disparities in outcomes that stem from information discrepancies in our model. To do so, we consider a population of agents who belong to different subgroups, which determine their knowledge about the deployed scoring rule. Agents within each subgroup observe the past scores received by their peers, which allow them to construct an estimate of the deployed scoring rule and to invest their efforts accordingly. The principal, taking into account the agents' behaviors, deploys a scoring rule that maximizes the social welfare of the whole population. We provide a collection of theoretical results that characterize the impact of the welfare-maximizing scoring rules on the strategic effort investments across different subgroups. In particular, we identify sufficient and necessary conditions for when the deployed scoring rule incentivizes optimal strategic investment across all groups for different notions of optimality. Finally, we complement and validate our theoretical analysis with experimental results on the real-world datasets Taiwan-Credit and Adult.
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. In this work, we analyze two popular post hoc interpretation techniques: SmoothGrad which is a gradient based method, and a variant of LIME which is a perturbation based method. More specifically, we derive explicit closed form expressions for the explanations output by these two methods and show that they both converge to the same explanation in expectation, i.e., when the number of perturbed samples used by these methods is large. We then leverage this connection to establish other desirable properties, such as robustness, for these techniques. We also derive finite sample complexity bounds for the number of perturbations required for these methods to converge to their expected explanation. Finally, we empirically validate our theory using extensive experimentation on both synthetic and real world datasets.
In many statistical problems, incorporating priors can significantly improve performance. However, the use of prior knowledge in differentially private query release has remained underexplored, despite such priors commonly being available in the form of public datasets, such as previous US Census releases. With the goal of releasing statistics about a private dataset, we present PMW^Pub, which -- unlike existing baselines -- leverages public data drawn from a related distribution as prior information. We provide a theoretical analysis and an empirical evaluation on the American Community Survey (ACS) and ADULT datasets, which shows that our method outperforms state-of-the-art methods. Furthermore, PMW^Pub scales well to high-dimensional data domains, where running many existing methods would be computationally infeasible.
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). We first provide a meaningful privacy formulation using the notion of joint differential privacy (JDP)--a strong variant of differential privacy for settings where each user receives their own sets of output (e.g., policy recommendations). We then develop a private optimism-based learning algorithm that simultaneously achieves strong PAC and regret bounds, and enjoys a JDP guarantee. Our algorithm only pays for a moderate privacy cost on exploration: in comparison to the non-private bounds, the privacy parameter only appears in lower-order terms. Finally, we present lower bounds on sample complexity and regret for reinforcement learning subject to JDP.
The use of machine learning (ML) systems in real-world applications entails more than just a prediction algorithm. AI for social good applications, and many real-world ML tasks in general, feature an iterative process which joins prediction, optimization, and data acquisition happen in a loop. We introduce bandit data-driven optimization, the first iterative prediction-prescription framework to formally analyze this practical routine. Bandit data-driven optimization combines the advantages of online bandit learning and offline predictive analytics in an integrated framework. It offers a flexible setup to reason about unmodeled policy objectives and unforeseen consequences. We propose PROOF, the first algorithm for this framework and show that it achieves no-regret. Using numerical simulations, we show that PROOF achieves superior performance over existing baseline.
Differentially private GANs have proven to be a promising approach for generating realistic synthetic data without compromising the privacy of individuals. However, due to the privacy-protective noise introduced in the training, the convergence of GANs becomes even more elusive, which often leads to poor utility in the output generator at the end of training. We propose Private post-GAN boosting (Private PGB), a differentially private method that combines samples produced by the sequence of generators obtained during GAN training to create a high-quality synthetic dataset. Our method leverages the Private Multiplicative Weights method (Hardt and Rothblum, 2010) and the discriminator rejection sampling technique (Azadi et al., 2019) for reweighting generated samples, to obtain high quality synthetic data even in cases where GAN training does not converge. We evaluate Private PGB on a Gaussian mixture dataset and two US Census datasets, and demonstrate that Private PGB improves upon the standard private GAN approach across a collection of quality measures. Finally, we provide a non-private variant of PGB that improves the data quality of standard GAN training.
Most online platforms strive to learn from interactions with consumers, and many engage in exploration: making potentially suboptimal choices for the sake of acquiring new information. We initiate a study of the interplay between exploration and competition: how such platforms balance the exploration for learning and the competition for consumers. Here consumers play three distinct roles: they are customers that generate revenue, they are sources of data for learning, and they are self-interested agents which choose among the competing platforms. We consider a stylized duopoly model in which two firms face the same multi-armed bandit instance. Users arrive one by one and choose between the two firms, so that each firm makes progress on its bandit instance only if it is chosen. We study whether and to what extent competition incentivizes the adoption of better bandit algorithms, and whether it leads to welfare increases for consumers. We find that stark competition induces firms to commit to a "greedy" bandit algorithm that leads to low consumer welfare. However, we find that weakening competition by providing firms with some "free" consumers incentivizes better exploration strategies and increases consumer welfare. We investigate two channels for weakening the competition: relaxing the rationality of consumers and giving one firm a first-mover advantage. We provide a mix of theoretical results and numerical simulations. Our findings are closely related to the "competition vs. innovation" relationship, a well-studied theme in economics. They also elucidate the first-mover advantage in the digital economy by exploring the role that data can play as a barrier to entry in online markets.
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. All three algorithms are \emph{oracle-efficient} in the sense that they are computationally efficient when given access to an optimization oracle. Such an oracle can be implemented using many existing (non-private) optimization tools such as sophisticated integer program solvers. While the accuracy of the synthetic data is contingent on the oracle's optimization performance, the algorithms satisfy differential privacy even in the worst case. For all three algorithms, we provide theoretical guarantees for both accuracy and privacy. Through empirical evaluation, we demonstrate that our methods scale well with both the dimensionality of the data and the number of queries. Compared to the state-of-the-art method High-Dimensional Matrix Mechanism \cite{McKennaMHM18}, our algorithms provide better accuracy in the large workload and high privacy regime (corresponding to low privacy loss $\varepsilon$).