arXiv subjects

Madeleine Pollack

Publications and source records attributed to Madeleine Pollack.

4 recordsLinked to original sources

arXiv2026

When Should AI Decide, Defer, and Deviate? Responsible Automation for Deceased Donor Kidney Allocation

We ask when an AI trained on historical decisions should be allowed to recommend decisions, defer to human experts, or in other cases, flag concerning patterns in data and deviate from past practice. This can be challenging because past decisions record what was done rather than what should have been done, and where data is sparse, a model's predictions may be too uncertain to act on. We provide a framework for addressing this problem using a case study in deceased-donor kidney allocation. Nearly 30% of kidneys recovered from deceased donors in the United States are never transplanted, largely because they are hard to place through the standard waitlist sequence. One can use AI to flag kidneys at risk of delayed or failed placement for out-of-sequence (OOS) allocation, but this comes at the cost of bypassing candidates higher on the waitlist. Thus, OOS allocation should only be used when the organ is demonstrably at high risk of discard on the standard sequence. Using Organ Procurement and Transplantation Network match-run data from 2016-2019 and 2023-2025 (excluding COVID-19-disrupted years), we build the Arbitrator framework, which combines various interpretable models and acts only when the uncertainty in their predictions cannot change the preferred action. Our Arbitrator resolves 93.5% of organ placement decisions using explicit medical criteria learned from data, and defers the remaining 6.5% to a human or a more complex model. We show that the Arbitrator correctly identifies 70.1% of historically discarded low-KDPI kidneys as OOS candidates, projecting that up to 43.9% of historically discarded kidneys could be flagged for expedited placement and potentially transplanted. We then exploit the interpretability of the Arbitrator to create an agentic audit comparing the learned rules to published clinical literature in order to flag decision-making patterns that are contentious.

cs.AI↗

arXiv2025

Navigating the Social Welfare Frontier: Portfolios for Multi-objective Reinforcement Learning

In many real-world applications of reinforcement learning (RL), deployed policies have varied impacts on different stakeholders, creating challenges in reaching consensus on how to effectively aggregate their preferences. Generalized $p$-means form a widely used class of social welfare functions for this purpose, with broad applications in fair resource allocation, AI alignment, and decision-making. This class includes well-known welfare functions such as Egalitarian, Nash, and Utilitarian welfare. However, selecting the appropriate social welfare function is challenging for decision-makers, as the structure and outcomes of optimal policies can be highly sensitive to the choice of $p$. To address this challenge, we study the concept of an $α$-approximate portfolio in RL, a set of policies that are approximately optimal across the family of generalized $p$-means for all $p \in [-\infty, 1]$. We propose algorithms to compute such portfolios and provide theoretical guarantees on the trade-offs among approximation factor, portfolio size, and computational efficiency. Experimental results on synthetic and real-world datasets demonstrate the effectiveness of our approach in summarizing the policy space induced by varying $p$ values, empowering decision-makers to navigate this landscape more effectively.

cs.LG↗

arXiv2025

Equitably allocating wildfire resilience investments for power grids: The curse of aggregation and vulnerability indices

Social vulnerability indices have increased traction for guiding infrastructure investment decisions to prioritize communities that need these investments most. One such plan is the Biden-Harris Justice40 initiative, which aims to guide equitable infrastructure investments by ensuring that disadvantaged communities defined by the Climate & Economic Justice Screening Tool (CEJST) receive 40% of the total benefit realized by the investment. However, there is limited research on the practicality of applying vulnerability indices like the CEJST to real-world decision-making for policy outcomes. In this paper, we study this gap by examining the effectiveness of vulnerability indices in a case study focused on power shutoff and undergrounding decisions in wildfire-prone regions. Using a mixed-integer program and a high-fidelity synthetic transmission network in Texas, we model resource allocation policies inspired by Justice40 and evaluate their impact on reducing power outages and mitigating wildfire risk for vulnerable groups. Our analysis reveals that the Justice40 framework may fail to protect certain communities facing high wildfire risk. In our case study, we show that indigenous groups are particularly impacted. We posit that this outcome is likely due to information losses from data aggregation and the use of generalized vulnerability indices. Through the use of explicit group-level protections, we are able to bound the best possible outcome for population groups that are proportionally most affected.

math.OC↗

arXiv2024

The implications of state aggregation in deteriorating Markov Decision Processes with optimal threshold policies

Markov Decision Processes (MDPs) are mathematical models of sequential decision-making under uncertainty that have found applications in healthcare, manufacturing, logistics, and others. In these models, a decision-maker observes the state of a stochastic process and determines which action to take with the goal of maximizing the expected total discounted rewards received. In many applications, the state space of the true system is large and there may be limited observations out of certain states to estimate the transition probability matrix. To overcome this, modelers will aggregate the true states into ``superstates" resulting in a smaller state space. This aggregation process improves computational tractability and increases the number of observations among superstates. Thus, the modeler's choice of state space leads to a trade-off in transition probability estimates. While coarser discretization of the state space gives more observations in each state to estimate the transition probability matrix, this comes at the cost of precision in the state characterization and resulting policy recommendations. In this paper, we consider the implications of this modeling decision on the resulting policies from MDPs for which the true model is expected to have a threshold policy that is optimal. We analyze these MDPs and provide conditions under which the aggregated MDP will also have an optimal threshold policy. Using a simulation study, we explore the trade-offs between more fine and more coarse aggregation. We explore the the show that there is the highest potential for policy improvement on larger state spaces, but that aggregated MDPs are preferable under limited data. We discuss how these findings the implications of our findings for modelers who must select which state space design to use.

math.OC↗