Tabular data is one of the most commonly used types of data in machine learning. Despite recent advances in neural nets (NNs) for tabular data, there is still an active discussion on whether or not NNs generally outperform gradient-boosted decision trees (GBDTs) on tabular data, with several recent works arguing either that GBDTs consistently outperform NNs on tabular data, or vice versa. In this work, we take a step back and question the importance of this debate. To this end, we conduct the largest tabular data analysis to date, comparing 19 algorithms across 176 datasets, and we find that the 'NN vs. GBDT' debate is overemphasized: for a surprisingly high number of datasets, either the performance difference between GBDTs and NNs is negligible, or light hyperparameter tuning on a GBDT is more important than choosing between NNs and GBDTs. Next, we analyze dozens of metafeatures to determine what \emph{properties} of a dataset make NNs or GBDTs better-suited to perform well. For example, we find that GBDTs are much better than NNs at handling skewed or heavy-tailed feature distributions and other forms of dataset irregularities. Our insights act as a guide for practitioners to determine which techniques may work best on their dataset. Finally, with the goal of accelerating tabular data research, we release the TabZilla Benchmark Suite: a collection of the 36 'hardest' of the datasets we study. Our benchmark suite, codebase, and all raw results are available at https://github.com/naszilla/tabzilla.

Clinical decision support (CDS) systems powered by predictive models have the potential to improve the accuracy and efficiency of clinical decision-making. However, without sufficient validation, these systems have the potential to mislead clinicians and harm patients. This is especially true for CDS systems used by opioid prescribers and dispensers, where a flawed prediction can directly harm patients. To prevent these harms, regulators and researchers have proposed guidance for validating predictive models and CDS systems. However, this guidance is not universally followed and is not required by law. We call on CDS developers, deployers, and users to hold these systems to higher standards of clinical and technical validation. We provide a case study on two CDS systems deployed on a national scale in the United States for predicting a patient's risk of adverse opioid-related events: the Stratification Tool for Opioid Risk Mitigation (STORM), used by the Veterans Health Administration, and NarxCare, a commercial system.

While other areas of machine learning have seen more and more automation, designing a high-performing recommender system still requires a high level of human effort. Furthermore, recent work has shown that modern recommender system algorithms do not always improve over well-tuned baselines. A natural follow-up question is, "how do we choose the right algorithm for a new dataset and performance metric?" In this work, we start by giving the first large-scale study of recommender system approaches by comparing 24 algorithms and 100 sets of hyperparameters across 85 datasets and 315 metrics. We find that the best algorithms and hyperparameters are highly dependent on the dataset and performance metric. However, there is also a strong correlation between the performance of each algorithm and various meta-features of the datasets. Motivated by these findings, we create RecZilla, a meta-learning approach to recommender systems that uses a model to predict the best algorithm and hyperparameters for new, unseen datasets. By using far more meta-training data than prior work, RecZilla is able to substantially reduce the level of human involvement when faced with a new recommender system application. We not only release our code and pretrained RecZilla models, but also all of our raw experimental results, so that practitioners can train a RecZilla model for their desired performance metric: https://github.com/naszilla/reczilla.

Algorithms for exchange of kidneys is one of the key successful applications in market design, artificial intelligence, and operations research. Potent immunosuppressant drugs suppress the body's ability to reject a transplanted organ up to the point that a transplant across blood- or tissue-type incompatibility becomes possible. In contrast to the standard kidney exchange problem, we consider a setting that also involves the decision about which recipients receive from the limited supply of immunosuppressants that make them compatible with originally incompatible kidneys. We firstly present a general computational framework to model this problem. Our main contribution is a range of efficient algorithms that provide flexibility in terms of meeting meaningful objectives. Motivated by the current reality of kidney exchanges using sophisticated mathematical-programming-based clearing algorithms, we then present a general but scalable approach to optimal clearing with immunosuppression; we validate our approach on realistic data from a large fielded exchange.

AI systems are often used to make or contribute to important decisions in a growing range of applications, including criminal justice, hiring, and medicine. Since these decisions impact human lives, it is important that the AI systems act in ways which align with human values. Techniques for preference modeling and social choice help researchers learn and aggregate peoples' preferences, which are used to guide AI behavior; thus, it is imperative that these learned preferences are accurate. These techniques often assume that people are willing to express strict preferences over alternatives; which is not true in practice. People are often indecisive, and especially so when their decision has moral implications. The philosophy and psychology literature shows that indecision is a measurable and nuanced behavior---and that there are several different reasons people are indecisive. This complicates the task of both learning and aggregating preferences, since most of the relevant literature makes restrictive assumptions on the meaning of indecision. We begin to close this gap by formalizing several mathematical indecision models based on theories from philosophy, psychology, and economics; these models can be used to describe (indecisive) agent decisions, both when they are allowed to express indecision and when they are not. We test these models using data collected from an online survey where participants choose how to (hypothetically) allocate organs to patients waiting for a transplant.

Given AI's growing role in modeling and improving decision-making, how and when to present users with feedback is an urgent topic to address. We empirically examined the effect of feedback from false AI on moral decision-making about donor kidney allocation. We found some evidence that judgments about whether a patient should receive a kidney can be influenced by feedback about participants' own decision-making perceived to be given by AI, even if the feedback is entirely random. We also discovered different effects between assessments presented as being from human experts and assessments presented as being from AI.

Bias in machine learning has manifested injustice in several areas, with notable examples including gender bias in job-related ads [4], racial bias in evaluating names on resumes [3], and racial bias in predicting criminal recidivism [1]. In response, research into algorithmic fairness has grown in both importance and volume over the past few years. Different metrics and approaches to algorithmic fairness have been proposed, many of which are based on prior legal and philosophical concepts [2]. The rapid expansion of this field makes it difficult for professionals to keep up, let alone the general public. Furthermore, misinformation about notions of fairness can have significant legal implications.

Bias in machine learning has manifested injustice in several areas, such as medicine, hiring, and criminal justice. In response, computer scientists have developed myriad definitions of fairness to correct this bias in fielded algorithms. While some definitions are based on established legal and ethical norms, others are largely mathematical. It is unclear whether the general public agrees with these fairness definitions, and perhaps more importantly, whether they understand these definitions. We take initial steps toward bridging this gap between ML researchers and the public, by addressing the question: does a lay audience understand a basic definition of ML fairness? We develop a metric to measure comprehension of three such definitions–demographic parity, equal opportunity, and equalized odds. We evaluate this metric using an online survey, and investigate the relationship between comprehension and sentiment, demographics, and the definition itself.

In barter exchanges, participants swap goods with one another without exchanging money; these exchanges are often facilitated by a central clearinghouse, with the goal of maximizing the aggregate quality (or number) of swaps. Barter exchanges are subject to many forms of uncertainty--in participant preferences, the feasibility and quality of various swaps, and so on. Our work is motivated by kidney exchange, a real-world barter market in which patients in need of a kidney transplant swap their willing living donors, in order to find a better match. Modern exchanges include 2- and 3-way swaps, making the kidney exchange clearing problem NP-hard. Planned transplants often \emph{fail} for a variety of reasons--if the donor organ is rejected by the recipient's medical team, or if the donor and recipient are found to be medically incompatible. Due to 2- and 3-way swaps, failed transplants can ``cascade'' through an exchange; one US-based exchange estimated that about $85\%$ of planned transplants failed in 2019. Many optimization-based approaches have been designed to avoid these failures; however most exchanges cannot implement these methods, due to legal and policy constraints. Instead, we consider a setting where exchanges can \emph{query} the preferences of certain donors and recipients--asking whether they would accept a particular transplant. We characterize this as a two-stage decision problem, in which the exchange program (a) queries a small number of transplants before committing to a matching, and (b) constructs a matching according to fixed policy. We show that selecting these edges is a challenging combinatorial problem, which is non-monotonic and non-submodular, in addition to being NP-hard. We propose both a greedy heuristic and a Monte Carlo tree search, which outperforms previous approaches, using experiments on both synthetic data and real kidney exchange data from the United Network for Organ Sharing.

Managing perishable inventory, such as blood stock awaiting use by patients in need, has been a topic of research for decades. This has been investigated across several disciplines: medical and social scientists have investigated who donates blood, how frequently, and why; management science researchers have long studied the blood supply chain from a logistical perspective. Yet global demand for blood still far exceeds supply, and unmet need is greatest in low- and middle-income countries. Both academics and policy experts suggest that large-scale coordination is necessary to alleviate demand for donor blood. Using the recently-deployed Facebook Blood Donation tool, we conduct the first large-scale algorithmic matching of blood donors with donation opportunities. In both simulations and real experiments we match potential donors with opportunities, guided by a machine learning model trained on prior observations of donor behavior. While measuring actual donation rates remains a challenge, we measure donor action (i.e., calling a blood bank or making an appointment) as a proxy for actual donation. Simulations suggest that even a simple matching strategy can increase donor action rate by 10-15%; a pilot experiment with real donors finds a slightly smaller increase of roughly 5%. While overall action rates remain low, even this modest increase among donors in a global network corresponds to many thousands of more potential donors taking action toward donation. Further, observing donor action on a social network can shed light onto donor behavior and response to incentives. Our initial findings align with several observations made in the medical and social science literature regarding donor behavior.

Patients with end-stage renal failure often find kidney donors who are willing to donate a life-saving kidney, but who are medically incompatible with the patients. Kidney exchanges are organized barter markets that allow such incompatible patient-donor pairs to enter as a single agent—where the patient is endowed with a donor “item”—and engage in trade with other similar agents, such that all agents “give” a donor organ if and only if they receive an organ in return. In practice, organized trades occur in large cyclic or chain-like structures, with multiple agents participating in the exchange event. Planned trades can fail for a variety of reasons, such as unforeseen logistical challenges, or changes in patient or donor health. These failures cause major inefficiency in fielded exchanges, as if even one individual trade fails in a planned cycle or chain, \emph{all or most of the resulting cycle or chain fails}. Ad-hoc, as well as optimization-based methods, have been developed to handle failure uncertainty; nevertheless, the majority of the existing methods use very simplified assumptions about failure uncertainty and/or are not scalable for real-world kidney exchanges.Motivated by kidney exchange, we study a stochastic cycle and chain packing problem, where we aim to identify structures in a directed graph to maximize the expectation of matched edge weights. All edges are subject to failure, and the failures can have nonidentical probabilities. To the best of our knowledge, the state-of-the-art approaches are only tractable when failure probabilities are identical. We formulate a relevant non-convex optimization problem and propose a tractable mixed-integer linear programming reformulation to solve it. In addition, we propose a model that integrates both risks and the expected utilities of the matching by incorporating conditional value at risk (CVaR) into the objective function, providing a robust formulation for this problem. Subsequently, we propose a sample-average-approximation (SAA) based approach to solve this problem. We test our approaches on data from the United Network for Organ Sharing (UNOS) and compare against state-of-the-art approaches. Our model provides better performance with the same running time as a leading deterministic approach (PICEF). Our CVaR extensions with an SAA-based method improves the $\alpha \times 100%$ ($0<\alpha\leq 1$) worst-case performance substantially compared to existing models.

In barter exchanges, participants directly trade their endowed goods in a constrained economic setting without money. Transactions in barter exchanges are often facilitated via a central clearinghouse that must match participants even in the face of uncertainty—over participants, existence and quality of potential trades, and so on. Leveraging robust combinatorial optimization techniques, we address uncertainty in kidney exchange, a real-world barter market where patients swap (in)compatible paired donors. We provide two scalable robust methods to handle two distinct types of uncertainty in kidney exchange—over the quality and the existence of a potential match. The latter case directly addresses a weakness in all stochastic-optimization-based methods to the kidney exchange clearing problem, which all necessarily require explicit estimates of the probability of a transaction existing—a still-unsolved problem in this nascent market. We also propose a novel, scalable kidney exchange formulation that eliminates the need for an exponential-time constraint generation process in competing formulations, maintains provable optimality, and serves as a subsolver for our robust approach. For each type of uncertainty we demonstrate the benefits of robustness on real data from a large, fielded kidney exchange in the United States. We conclude by drawing parallels between robustness and notions of fairness in the kidney exchange setting.

Artificial Intelligence (AI) ethics is by no means a new discipline; thinkers like Asimov and Philip K Dick laid the foundations of this field decades ago. Both then and today, popular dilemmas in AI ethics largely focus on artificial consciousness, artificial general intelligence, autonomous weapons, and some version of the trolley problem. While these thought experiments may prove useful in the future, modern AI applications that are in use today raise ethical dilemmas that require urgent resolution. Public outcry in response to AI in health care, criminal justice, and employment highlight the urgency of the matter. These real and imminent ethical challenges posed by AI form the basis of my dissertation research. In particular, I focus on domains where AI is necessary or inevitable -- such as kidney exchange and medical image classification -- and ethical challenges are unavoidable.

Balancing fairness and efficiency in resource allocation is a classical economic and computational problem. The price of fairness measures the worst-case loss of economic efficiency when using an inefficient but fair allocation rule; for indivisible goods in many settings, this price is unacceptably high. One such setting is kidney exchange, where needy patients swap willing but incompatible kidney donors. In this work, we close an open problem regarding the theoretical price of fairness in modern kidney exchanges. We then propose a general hybrid fairness rule that balances a strict lexicographic preference ordering over classes of agents, and a utilitarian objective that maximizes economic efficiency. We develop a utility function for this rule that favors disadvantaged groups lexicographically; but if cost to overall efficiency becomes too high, it switches to a utilitarian objective. This rule has only one parameter which is proportional to a bound on the price of fairness, and can be adjusted by policymakers. We apply this rule to real data from a large kidney exchange and show that our hybrid rule produces more reliable outcomes than other fairness rules.

In this work, we close an open theoretical problem regarding the price of fairness in modern kidney exchanges. We then propose a hybrid fairness rule that balances a lexicographic preference ordering over agents, with a utilitarian objective. This rule has one parameter which controls a bound on the price of fairness. We apply this rule to real data from a large kidney exchange and show that our hybrid rule produces more reliable outcomes than other fairness rules.

Physiologically inspired feature extraction for audio classification often uses simplified parametric models of auditory processing. We employ linear and nonlinear neuron models directly derived from neural responses in zebra finches as feature extraction front-ends. The most important features were identified using automatic feature selection techniques. This allows both a quantitative evaluation of neural features for sound classification tasks in terms of classification accuracy and a qualitative analysis of the auditory features that are most relevant. It turned out that a relatively small subpopulation of neural responses is sufficient to achieve reasonable classification performance. For linear as well as for nonlinear neuron models, we found three different shapes of spectro-temporal features to be archetypical. The relation of these to analytic approaches (such as Gabor filters) is discussed. The overall classification rates in a 6-class task reached up to 94% accuracy. Nonlinear models provided up to 15% benefit over linear models, indicating the importance of nonlinearities in classification with physiologically motivated features.