Lydia T. Liu

Romina Mahinpei, Victoria Dean, Ruth Fong et al.

AI systems increasingly shape human workflows by generating intermediate artifacts that users can adopt, revise, or ignore. While prior work has shown that AI assistance can improve the efficiency and accuracy of required tasks, less is known about whether it can increase participation in discretionary but beneficial work that users often intend to perform but frequently skip. We study this question in the context of personalized feedback provision in higher education, a pedagogically valuable but often optional practice. We conduct a mixed-methods study combining a randomized field experiment and qualitative interviews in a 300-level machine learning course with n=11 teaching assistants (TAs) and n=88 students. Student submissions were randomly assigned to either (1) a treatment condition where TAs received AI-assisted feedback drafts after grading or (2) a control condition without drafts. TAs remained fully in control and could use, edit, or ignore drafts at their discretion. We find that AI-assisted feedback significantly increases feedback provision (+10.8 percentage points, SE=1.1, p<0.001) and feedback length (+39.8 chars, SE=3.45, p<0.001) without negatively affecting student usefulness ratings or reducing time per character. Qualitative findings suggest that AI-assisted drafts function as editable scaffolds that lower barriers to initiating feedback rather than reducing overall effort. Our findings highlight AI's promise for discretionary but beneficial tasks: increasing work that might otherwise go undone while preserving human control over final outcomes.

Lydia T. Liu, Solon Barocas, Jon Kleinberg et al.

Predicting future outcomes is a prevalent application of machine learning in social impact domains. Examples range from predicting student success in education to predicting disease risk in healthcare. Practitioners recognize that the ultimate goal is not just to predict but to act effectively. Increasing evidence suggests that relying on outcome predictions for downstream interventions may not have desired results. In most domains there exists a multitude of possible interventions for each individual, making the challenge of taking effective action more acute. Even when causal mechanisms connecting the individual's latent states to outcomes is well understood, in any given instance (a specific student or patient), practitioners still need to infer -- from budgeted measurements of latent states -- which of many possible interventions will be most effective for this individual. With this in mind, we ask: when are accurate predictors of outcomes helpful for identifying the most suitable intervention? Through a simple model encompassing actions, latent states, and measurements, we demonstrate that pure outcome prediction rarely results in the most effective policy for taking actions, even when combined with other measurements. We find that except in cases where there is a single decisive action for improving the outcome, outcome prediction never maximizes "action value", the utility of taking actions. Making measurements of actionable latent states, where specific actions lead to desired outcomes, considerably enhances the action value compared to outcome prediction, and the degree of improvement depends on action costs and the outcome model. This analysis emphasizes the need to go beyond generic outcome prediction in interventional settings by incorporating knowledge of plausible actions and latent states.

Lydia T. Liu, Serena Wang, Tolani Britton et al.

Machine learning (ML) techniques are increasingly prevalent in education, from their use in predicting student dropout, to assisting in university admissions, and facilitating the rise of MOOCs. Given the rapid growth of these novel uses, there is a pressing need to investigate how ML techniques support long-standing education principles and goals. In this work, we shed light on this complex landscape drawing on qualitative insights from interviews with education experts. These interviews comprise in-depth evaluations of ML for education (ML4Ed) papers published in preeminent applied ML conferences over the past decade. Our central research goal is to critically examine how the stated or implied education and societal objectives of these papers are aligned with the ML problems they tackle. That is, to what extent does the technical problem formulation, objectives, approach, and interpretation of results align with the education problem at hand. We find that a cross-disciplinary gap exists and is particularly salient in two parts of the ML life cycle: the formulation of an ML problem from education goals and the translation of predictions to interventions. We use these insights to propose an extended ML life cycle, which may also apply to the use of ML in other domains. Our work joins a growing number of meta-analytical studies across education and ML research, as well as critical analyses of the societal impact of ML. Specifically, it fills a gap between the prevailing technical understanding of machine learning and the perspective of education researchers working with students and in policy.

Mark D. Verhagen, Benedikt Stroebl, Tiffany Liu et al.

For over a century, life course researchers have faced a choice between two dominant methodological approaches: qualitative methods that analyze rich data but are constrained to small samples, and quantitative survey-based methods that study larger populations but sacrifice data richness for scale. Two recent technological developments now enable us to imagine a hybrid approach that combines some of the depth of the qualitative approach with the scale of quantitative methods. The first development is the steady rise of ''complex log data,'' behavioral data that is logged for purposes other than research but that can be repurposed to construct rich accounts of people's lives. The second is the emergence of large language models (LLMs) with exceptional pattern recognition capabilities on plain text. In this paper, we take a necessary step toward creating this hybrid approach by developing a flexible procedure to transform complex log data into a textual representation of an individual's life trajectory across multiple domains, over time, and in context. We call this data representation a ''book of life.'' We illustrate the feasibility of our approach by writing over 100 million books of life covering many different facets of life, over time and placed in social context using Dutch population-scale registry data. We open source the book of life toolkit (BOLT), and invite the research community to explore the many potential applications of this approach.

Lydia T. Liu, Inioluwa Deborah Raji, Angela Zhou et al.

Many automated decision systems (ADS) are designed to solve prediction problems -- where the goal is to learn patterns from a sample of the population and apply them to individuals from the same population. In reality, these prediction systems operationalize holistic policy interventions in deployment. Once deployed, ADS can shape impacted population outcomes through an effective policy change in how decision-makers operate, while also being defined by past and present interactions between stakeholders and the limitations of existing organizational, as well as societal, infrastructure and context. In this work, we consider the ways in which we must shift from a prediction-focused paradigm to an interventionist paradigm when considering the impact of ADS within social systems. We argue this requires a new default problem setup for ADS beyond prediction, to instead consider predictions as decision support, final decisions, and outcomes. We highlight how this perspective unifies modern statistical frameworks and other tools to study the design, implementation, and evaluation of ADS systems, and point to the research directions necessary to operationalize this paradigm shift. Using these tools, we characterize the limitations of focusing on isolated prediction tasks, and lay the foundation for a more intervention-oriented approach to developing and deploying ADS.

Lydia T. Liu, Nikhil Garg, Christian Borgs

Strategic classification studies the design of a classifier robust to the manipulation of input by strategic individuals. However, the existing literature does not consider the effect of competition among individuals as induced by the algorithm design. Motivated by constrained allocation settings such as college admissions, we introduce strategic ranking, in which the (designed) individual reward depends on an applicant's post-effort rank in a measurement of interest. Our results illustrate how competition among applicants affects the resulting equilibria and model insights. We analyze how various ranking reward designs, belonging to a family of step functions, trade off applicant, school, and societal utility, as well as how ranking design counters inequities arising from disparate access to resources. In particular, we find that randomization in the reward design can mitigate two measures of disparate impact, welfare gap and access.

Lydia T. Liu, Feng Ruan, Horia Mania et al.

We study two-sided matching markets in which one side of the market (the players) does not have a priori knowledge about its preferences for the other side (the arms) and is required to learn its preferences from experience. Also, we assume the players have no direct means of communication. This model extends the standard stochastic multi-armed bandit framework to a decentralized multiple player setting with competition. We introduce a new algorithm for this setting that, over a time horizon $T$, attains $\mathcal{O}(\log(T))$ stable regret when preferences of the arms over players are shared, and $\mathcal{O}(\log(T)^2)$ regret when there are no assumptions on the preferences on either side. Moreover, in the setting where a single player may deviate, we show that the algorithm is incentive compatible whenever the arms' preferences are shared, but not necessarily so when preferences are fully general.

Esther Rolf, Max Simchowitz, Sarah Dean et al.

While real-world decisions involve many competing objectives, algorithmic decisions are often evaluated with a single objective function. In this paper, we study algorithmic policies which explicitly trade off between a private objective (such as profit) and a public objective (such as social welfare). We analyze a natural class of policies which trace an empirical Pareto frontier based on learned scores, and focus on how such decisions can be made in noisy or data-limited regimes. Our theoretical results characterize the optimal strategies in this class, bound the Pareto errors due to inaccuracies in the scores, and show an equivalence between optimal strategies and a rich class of fairness-constrained profit-maximizing policies. We then present empirical results in two different contexts -- online content recommendation and sustainable abalone fisheries -- to underscore the applicability of our approach to a wide range of practical decisions. Taken together, these results shed light on inherent trade-offs in using machine learning for decisions that impact social welfare.

Lydia T. Liu, Horia Mania, Michael I. Jordan

Stable matching, a classical model for two-sided markets, has long been studied with little consideration for how each side's preferences are learned. With the advent of massive online markets powered by data-driven matching platforms, it has become necessary to better understand the interplay between learning and market objectives. We propose a statistical learning model in which one side of the market does not have a priori knowledge about its preferences for the other side and is required to learn these from stochastic rewards. Our model extends the standard multi-armed bandits framework to multiple players, with the added feature that arms have preferences over players. We study both centralized and decentralized approaches to this problem and show surprising exploration-exploitation trade-offs compared to the single player multi-armed bandits setting.

Zhizhen Zhao, Lydia T. Liu, Amit Singer

In photon-limited imaging, the pixel intensities are affected by photon count noise. Many applications, such as 3-D reconstruction using correlation analysis in X-ray free electron laser (XFEL) single molecule imaging, require an accurate estimation of the covariance of the underlying 2-D clean images. Accurate estimation of the covariance from low-photon count images must take into account that pixel intensities are Poisson distributed, hence the classical sample covariance estimator is sub-optimal. Moreover, in single molecule imaging, including in-plane rotated copies of all images could further improve the accuracy of covariance estimation. In this paper we introduce an efficient and accurate algorithm for covariance matrix estimation of count noise 2-D images, including their uniform planar rotations and possibly reflections. Our procedure, steerable $e$PCA, combines in a novel way two recently introduced innovations. The first is a methodology for principal component analysis (PCA) for Poisson distributions, and more generally, exponential family distributions, called $e$PCA. The second is steerable PCA, a fast and accurate procedure for including all planar rotations for PCA. The resulting principal components are invariant to the rotation and reflection of the input images. We demonstrate the efficiency and accuracy of steerable $e$PCA in numerical experiments involving simulated XFEL datasets and rotated Yale B face data.

Lydia T. Liu, Max Simchowitz, Moritz Hardt

We clarify what fairness guarantees we can and cannot expect to follow from unconstrained machine learning. Specifically, we characterize when unconstrained learning on its own implies group calibration, that is, the outcome variable is conditionally independent of group membership given the score. We show that under reasonable conditions, the deviation from satisfying group calibration is upper bounded by the excess risk of the learned score relative to the Bayes optimal score function. A lower bound confirms the optimality of our upper bound. Moreover, we prove that as the excess risk of the learned score decreases, it strongly violates separation and independence, two other standard fairness criteria. Our results show that group calibration is the fairness criterion that unconstrained learning implicitly favors. On the one hand, this means that calibration is often satisfied on its own without the need for active intervention, albeit at the cost of violating other criteria that are at odds with calibration. On the other hand, it suggests that we should be satisfied with calibration as a fairness criterion only if we are at ease with the use of unconstrained machine learning in a given application.

Chi Jin, Lydia T. Liu, Rong Ge et al.

Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex nonsmooth losses (such as modern deep networks), the population risk is generally significantly more well-behaved from an optimization point of view than the empirical risk. In particular, sampling can create many spurious local minima. We consider a general framework which aims to optimize a smooth nonconvex function $F$ (population risk) given only access to an approximation $f$ (empirical risk) that is pointwise close to $F$ (i.e., $\|F-f\|_{\infty} \le ν$). Our objective is to find the $ε$-approximate local minima of the underlying function $F$ while avoiding the shallow local minima---arising because of the tolerance $ν$---which exist only in $f$. We propose a simple algorithm based on stochastic gradient descent (SGD) on a smoothed version of $f$ that is guaranteed to achieve our goal as long as $ν\le O(ε^{1.5}/d)$. We also provide an almost matching lower bound showing that our algorithm achieves optimal error tolerance $ν$ among all algorithms making a polynomial number of queries of $f$. As a concrete example, we show that our results can be directly used to give sample complexities for learning a ReLU unit.

Lydia T. Liu, Sarah Dean, Esther Rolf et al.

Fairness in machine learning has predominantly been studied in static classification settings without concern for how decisions change the underlying population over time. Conventional wisdom suggests that fairness criteria promote the long-term well-being of those groups they aim to protect. We study how static fairness criteria interact with temporal indicators of well-being, such as long-term improvement, stagnation, and decline in a variable of interest. We demonstrate that even in a one-step feedback model, common fairness criteria in general do not promote improvement over time, and may in fact cause harm in cases where an unconstrained objective would not. We completely characterize the delayed impact of three standard criteria, contrasting the regimes in which these exhibit qualitatively different behavior. In addition, we find that a natural form of measurement error broadens the regime in which fairness criteria perform favorably. Our results highlight the importance of measurement and temporal modeling in the evaluation of fairness criteria, suggesting a range of new challenges and trade-offs.