Off-policy Evaluation (OPE) methods are a crucial tool for evaluating policies in high-stakes domains such as healthcare, where exploration is often infeasible, unethical, or expensive. However, the extent to which such methods can be trusted under adversarial threats to data quality is largely unexplored. In this work, we make the first attempt at investigating the sensitivity of OPE methods to marginal adversarial perturbations to the data. We design a generic data poisoning attack framework leveraging influence functions from robust statistics to carefully construct perturbations that maximize error in the policy value estimates. We carry out extensive experimentation with multiple healthcare and control datasets. Our results demonstrate that many existing OPE methods are highly prone to generating value estimates with large errors when subject to data poisoning attacks, even for small adversarial perturbations. These findings question the reliability of policy values derived using OPE methods and motivate the need for developing OPE methods that are statistically robust to train-time data poisoning attacks.
The performance of machine learning models heavily depends on the quality of input data, yet real-world applications often encounter various data-related challenges. One such challenge could arise when curating training data or deploying the model in the real world - two comparable datasets in the same domain may have different distributions. While numerous techniques exist for detecting distribution shifts, the literature lacks comprehensive approaches for explaining dataset differences in a human-understandable manner. To address this gap, we propose a suite of interpretable methods (toolbox) for comparing two datasets. We demonstrate the versatility of our approach across diverse data modalities, including tabular data, language, images, and signals in both low and high-dimensional settings. Our methods not only outperform comparable and related approaches in terms of explanation quality and correctness, but also provide actionable, complementary insights to understand and mitigate dataset differences effectively.
Even if a model is not globally sparse, it is possible for decisions made from that model to be accurately and faithfully described by a small number of features. For instance, an application for a large loan might be denied to someone because they have no credit history, which overwhelms any evidence towards their creditworthiness. In this work, we introduce the Sparse Explanation Value (SEV), a new way of measuring sparsity in machine learning models. In the loan denial example above, the SEV is 1 because only one factor is needed to explain why the loan was denied. SEV is a measure of decision sparsity rather than overall model sparsity, and we are able to show that many machine learning models -- even if they are not sparse -- actually have low decision sparsity, as measured by SEV. SEV is defined using movements over a hypercube, allowing SEV to be defined consistently over various model classes, with movement restrictions reflecting real-world constraints. We proposed the algorithms that reduce SEV without sacrificing accuracy, providing sparse and completely faithful explanations, even without globally sparse models.
Interpretability is crucial for doctors, hospitals, pharmaceutical companies and biotechnology corporations to analyze and make decisions for high stakes problems that involve human health. Tree-based methods have been widely adopted for \textit{survival analysis} due to their appealing interpretablility and their ability to capture complex relationships. However, most existing methods to produce survival trees rely on heuristic (or greedy) algorithms, which risk producing sub-optimal models. We present a dynamic-programming-with-bounds approach that finds provably-optimal sparse survival tree models, frequently in only a few seconds.
Many modern causal questions ask how treatments affect complex outcomes that are measured using wearable devices and sensors. Current analysis approaches require summarizing these data into scalar statistics (e.g., the mean), but these summaries can be misleading. For example, disparate distributions can have the same means, variances, and other statistics. Researchers can overcome the loss of information by instead representing the data as distributions. We develop an interpretable method for distributional data analysis that ensures trustworthy and robust decision-making: Analyzing Distributional Data via Matching After Learning to Stretch (ADD MALTS). We (i) provide analytical guarantees of the correctness of our estimation strategy, (ii) demonstrate via simulation that ADD MALTS outperforms other distributional data analysis methods at estimating treatment effects, and (iii) illustrate ADD MALTS' ability to verify whether there is enough cohesion between treatment and control units within subpopulations to trustworthily estimate treatment effects. We demonstrate ADD MALTS' utility by studying the effectiveness of continuous glucose monitors in mitigating diabetes risks.
This paper explores the challenges in evaluating machine learning (ML) models for continuous health monitoring using wearable devices beyond conventional metrics. We state the complexities posed by real-world variability, disease dynamics, user-specific characteristics, and the prevalence of false notifications, necessitating novel evaluation strategies. Drawing insights from large-scale heart studies, the paper offers a comprehensive guideline for robust ML model evaluation on continuous health monitoring.
Prediction of mortality in intensive care unit (ICU) patients is an important task in critical care medicine. Prior work in creating mortality risk models falls into two major categories: domain-expert-created scoring systems, and black box machine learning (ML) models. Both of these have disadvantages: black box models are unacceptable for use in hospitals, whereas manual creation of models (including hand-tuning of logistic regression parameters) relies on humans to perform high-dimensional constrained optimization, which leads to a loss in performance. In this work, we bridge the gap between accurate black box models and hand-tuned interpretable models. We build on modern interpretable ML techniques to design accurate and interpretable mortality risk scores. We leverage the largest existing public ICU monitoring datasets, namely the MIMIC III and eICU datasets. By evaluating risk across medical centers, we are able to study generalization across domains. In order to customize our risk score models, we develop a new algorithm, GroupFasterRisk, which has several important benefits: (1) it uses hard sparsity constraint, allowing users to directly control the number of features; (2) it incorporates group sparsity to allow more cohesive models; (3) it allows for monotonicity correction on models for including domain knowledge; (4) it produces many equally-good models at once, which allows domain experts to choose among them. GroupFasterRisk creates its risk scores within hours, even on the large datasets we study here. GroupFasterRisk's risk scores perform better than risk scores currently used in hospitals, and have similar prediction performance to black box ML models (despite being much sparser). Because GroupFasterRisk produces a variety of risk scores and handles constraints, it allows design flexibility, which is the key enabler of practical and trustworthy model creation.
The Rashomon set is the set of models that perform approximately equally well on a given dataset, and the Rashomon ratio is the fraction of all models in a given hypothesis space that are in the Rashomon set. Rashomon ratios are often large for tabular datasets in criminal justice, healthcare, lending, education, and in other areas, which has practical implications about whether simpler models can attain the same level of accuracy as more complex models. An open question is why Rashomon ratios often tend to be large. In this work, we propose and study a mechanism of the data generation process, coupled with choices usually made by the analyst during the learning process, that determines the size of the Rashomon ratio. Specifically, we demonstrate that noisier datasets lead to larger Rashomon ratios through the way that practitioners train models. Additionally, we introduce a measure called pattern diversity, which captures the average difference in predictions between distinct classification patterns in the Rashomon set, and motivate why it tends to increase with label noise. Our results explain a key aspect of why simpler models often tend to perform as well as black box models on complex, noisier datasets.
We present ProtoConcepts, a method for interpretable image classification combining deep learning and case-based reasoning using prototypical parts. Existing work in prototype-based image classification uses a ``this looks like that'' reasoning process, which dissects a test image by finding prototypical parts and combining evidence from these prototypes to make a final classification. However, all of the existing prototypical part-based image classifiers provide only one-to-one comparisons, where a single training image patch serves as a prototype to compare with a part of our test image. With these single-image comparisons, it can often be difficult to identify the underlying concept being compared (e.g., ``is it comparing the color or the shape?''). Our proposed method modifies the architecture of prototype-based networks to instead learn prototypical concepts which are visualized using multiple image patches. Having multiple visualizations of the same prototype allows us to more easily identify the concept captured by that prototype (e.g., ``the test image and the related training patches are all the same shade of blue''), and allows our model to create richer, more interpretable visual explanations. Our experiments show that our ``this looks like those'' reasoning process can be applied as a modification to a wide range of existing prototypical image classification networks while achieving comparable accuracy on benchmark datasets.
Recent statistical and reinforcement learning methods have significantly advanced patient care strategies. However, these approaches face substantial challenges in high-stakes contexts, including missing data, inherent stochasticity, and the critical requirements for interpretability and patient safety. Our work operationalizes a safe and interpretable framework to identify optimal treatment regimes. This approach involves matching patients with similar medical and pharmacological characteristics, allowing us to construct an optimal policy via interpolation. We perform a comprehensive simulation study to demonstrate the framework's ability to identify optimal policies even in complex settings. Ultimately, we operationalize our approach to study regimes for treating seizures in critically ill patients. Our findings strongly support personalized treatment strategies based on a patient's medical history and pharmacological features. Notably, we identify that reducing medication doses for patients with mild and brief seizure episodes while adopting aggressive treatment for patients in intensive care unit experiencing intense seizures leads to more favorable outcomes.