Searcharxiv⌕ Search

arXiv subjects

Sanmay Das

Publications and source records attributed to Sanmay Das.

At least 19 recordsLinked to original sources
arXiv2026

Scarcity and Predictive Uncertainty: Implications for Societal Resource Allocation

An emerging literature examines the critical question of when and how prediction can be useful in allocating scarce societal resources. We examine a novel variant of this question: What happens when predictive uncertainty differs systematically across the population? This can occur in several situations; for example, when machine learning models have significantly different accuracies across different demographics. We show that this uncertainty has serious implications for resource allocation when coupled with commonly used binary measures of societal benefit from allocation. We formulate a novel mathematical model of scarce resource allocation that accounts for heterogeneous predictive uncertainties and analyze implications for both the allocation mechanism and the realized population-level benefits. We find that when resources are very scarce, maximum marginal benefit (MMB) prioritization favors individuals with lower predictive uncertainty even at the identical underlying initial state. However, we observe a flip in prioritization when resources are abundant, targeting higher-uncertainty individuals. We illustrate the implications of our results on the PISA educational testing dataset. Our findings have meaningful ramifications for the distributional outcomes of prioritization policies in many domains touched by the theory of local justice, including the allocation of public education resources, medical triage, and homelessness services. They also reveal a new moral dilemma in the ethics of scarce resource allocation - is it just to allocate a resource to one person over another solely based on predictive uncertainty about their futures? We also assess efficiency losses under both MMB and the vulnerability-first (VF) prioritization. Our model predicts efficiency losses across all resource levels, but particularly in low-resource settings.

cs.CY↗
arXiv2026

Benchmarking Geospatial Foundation Models for Agriculture Applications

Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic transferability has not been systematically tested, especially in agriculture applications. This paper presents a controlled benchmark that evaluates three models, Prithvi, SpectralGPT, and SatMAE, on multi-temporal crop segmentation and change detection across four U.S. states, Iowa, North Carolina, California, and Minnesota. By assigning each train, validation, and test split to a separate region, we measure how well each model transfers to land it has not seen. All three degrade sharply under regional distribution shift, predicting only the most common crops while missing rare ones. We further find that fitting these models to a shared input format affects each one differently, which complicates direct architectural comparison. These results expose key limitations of current geospatial foundation models for agriculture and point to region aware evaluation as a necessary standard.

cs.CV↗
arXiv2026

Can LLMs Rank? A Tale of Triads and Triage

From housing allocation for households experiencing homelessness to triage in emergency departments, LLMs are increasingly being considered as judges of consequential decisions that require ranking people for scarce resources. Ranking large groups simultaneously is cognitively demanding and error-prone. A natural solution, drawing on decades of social choice theory, elicits pairwise comparisons and aggregates them into a total order. However, a fundamental question remains when LLMs serve as the pairwise judge: how can a practitioner tell, before committing to a ranking, whether the LLM's judgments are sufficiently consistent to trust the result? We discuss two different ways of identifying consistency. A classical diagnostic, the coefficient of consistency $\zeta$, originally developed to measure judge reliability by counting circular triads in tournament graphs, provides a cheap, model-free measure of intra-run consistency. Various standard measures of distance between rankings, for example Kendall's $\tau$, can measure inter-run variability. We show, in both theory and practice, that these measures are independently valuable, and advocate for using both to assess reliability of rankings. We demonstrate the practical importance of our results across two high-stakes prioritization tasks: homelessness service allocation and emergency department triage. Three different leading LLMs have considerably different performance profiles across these two axes of consistency. We provide guidelines for how practitioners could think about measuring and assessing consistency before committing to a model for ranking or prioritization.

cs.CY↗
arXiv2026

Optimally Auditing Adversarial Agents

Fraud can pose a challenge in many resource allocation domains, including social service delivery and credit provision. For example, agents may misreport private information in order to gain benefits or access to credit. To mitigate this, a principal can design strategic audits to verify claims and penalize misreporting. In this paper, we introduce a general model of audit policy design as a principal-agent game with multiple agents, where the principal commits to an audit policy, and agents collectively choose an equilibrium that minimizes the principal's utility. We examine both adaptive and non-adaptive settings, depending on whether the principal's policy can be responsive to the distribution of agent reports. Our work provides efficient algorithms for computing optimal audit policies in both settings and extends these results to a setting with limited audit budgets.

cs.GT↗
arXiv2026

Federated Parameter-Efficient Adaptation for Interference Mitigation at the Wireless Edge

Dense wireless deployments face co-channel interference from heterogeneous sources that vary across base stations (gNBs in 5G). While centralized DNN-based approaches to interference mitigation have shown strong performance, deploying and adapting these models across distributed gNBs via federated learning (FL) requires transmitting full model updates each round, resulting in a cost that scales poorly with network density. Parameter-efficient fine-tuning (PEFT) reduces this burden by training and communicating only a small fraction of parameters. While traditionally applied to large foundation models, we adapt Low-Rank Adaptation (LoRA) to temporal convolutional neural network architectures for interference suppression, placing low-rank adapters on the dilated convolutional layers. This placement enables LoRA to learn local interference-specific temporal patterns, while the frozen backbone retains the shared signal extraction capability. These lightweight adapters (5.1\% of backbone parameters) are federated via FedAvg, reducing per-round communication by up to 20$\times$ compared to federating full model updates. We evaluate various PEFT strategies across simulated distributed gNBs with non-IID interference environments. Results show that local LoRA achieves 12.8\% average BER improvement over the frozen backbone, while Fed-LoRA achieves comparable performance (12.6\%). Fed-LoRA outperforms local adaptation on data-starved nodes where federated knowledge transfer compensates for limited samples, all while avoiding the catastrophic degradation observed with full-model FedAvg under heterogeneous conditions.

cs.NI↗
arXiv2026

Adversarial Data Modeling in Epidemiology

Epidemiological models increasingly rely on crowdsourced, self-reported behavioral data such as vaccination status, mask usage, and social distancing adherence. This data, however, is not passively sampled but instead strategically reported, making it a canonical case of adversarial input to a data mining pipeline. Individuals misreport for various reasons, e.g., to avoid penalties, to access benefits, or to express distrust in public health authorities. We introduce a data-modeling framework that casts the interaction between the population and a public health authority as a signaling game. This approach provides both a generative model of strategically-corrupted behavioral data and a mechanism for the receiver to recover reliable signal from it. Individuals (senders) choose how to report their behaviors, while the public health authority (receiver) updates their epidemiological model(s) based on potentially distorted signals, and modifies its trust in incoming reports accordingly. Focusing on deception around masking and vaccination, we characterize analytically game equilibrium outcomes as distinct regimes of data corruption, and evaluate the degree to which deception can be tolerated while maintaining epidemic control through policy interventions. In large scale simulations, our results show that even under pervasive dishonesty in pooling equilibria, well-designed sender and receiver strategies can still maintain effective epidemic control. Real-world validation further shows that behavioral distortions often exhibit structured patterns rather than arbitrary noise. This work advances the understanding of adversarial data in epidemiology and offers tools for designing more robust public health models in the presence of strategic user behavior.

cs.GT↗
arXiv2026

SMaRT: Online Reusable Resource Assignment and an Application to Mediation in the Kenyan Judiciary

Motivated by the problem of assigning mediators to cases in the Kenyan judicial system, we study an online resource allocation problem where incoming tasks (cases) must be immediately assigned to available, capacity-constrained resources (mediators). The resources differ in their quality, which may need to be learned. In addition, resources can only be assigned to a subset of tasks that overlaps to varying degrees with the subset of tasks other resources can be assigned to. The objective is to maximize task completion while satisfying soft capacity constraints across all the resources. The scale of the real-world problem poses substantial challenges, since there are over 2000 mediators, and a multitude of combinations of geographic locations (87) and case types (12) that each mediator is qualified to work on. Together, these features-unknown quality of new resources (newly onboarded mediators), soft capacity constraints (due to the mandate to assign cases without delay), and high-dimensional state space-make existing scheduling and resource allocation algorithms either inapplicable or inefficient. We formalize the problem in a tractable manner, using a quadratic program formulation for assignment and a multi-agent bandit style framework for learning. We demonstrate the key properties and advantages of our new algorithm, SMaRT (Selecting Mediators that are Right for the Task), compared with baselines on some stylized instances of the mediator allocation problem. We then turn to considering its application to real-world data on cases and mediators from the Kenyan Judiciary. SMaRT outperforms baselines and allows for controlling the tradeoff between the strictness of the capacity constraints and overall case resolution rates, both in situations where mediator quality is known beforehand and when the problem is bandit-like in that learning is part of the problem definition.

cs.CY↗
arXiv2026

Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making

Street-level bureaucrats, such as caseworkers and border guards routinely face the dilemma of whether to follow rigid policy or exercise discretion based on professional judgement. However, frequent overrides threaten consistency and introduce bias, explaining why bureaucracies often ration discretion as a finite resource. While prior work models discretion as a static cost-benefit tradeoff, we lack a principled model of how discretion should be rationed over time under real operational constraints. We formalize discretion as a dynamic allocation problem in which an agent receives stochastic opportunities to improve upon a default policy and must spend a limited override budget K over a finite horizon T. We show that overrides follow a dynamic threshold rule: use discretion only when the opportunity exceeds a time and budget-dependent cutoff. Our main theoretical contribution identifies a behavioral invariance: for location-scale families of improvement distributions, the rate at which an optimal agent exercises discretion is independent of the scale of potential gains and depends only on the distribution's shape (e.g., tail heaviness). This result implies systematic differences in discretionary "policy personality." When gains are fat-tailed, optimal agents are patient, conserving discretion for outliers. When gains are thin-tailed, agents spend more routinely. We illustrate these implications using data from a homelessness services system. Discretionary overrides track operational constraints: they are higher at the start of the workweek, suppressed on weekends when intake is offline, and shift with short-run housing capacity. These results suggest that discretion can be both procedurally constrained and welfare-improving when treated as an explicitly budgeted resource, providing a foundation for auditing override patterns and designing decision-support systems.

cs.CY↗
arXiv2025

Fixed Points and Stochastic Meritocracies: A Long-Term Perspective

We study group fairness in the context of feedback loops induced by meritocratic selection into programs that themselves confer additional advantage, like college admissions. We introduce a stylized, yet novel inter-generational model for the setting and analyze it in situations where there are no underlying differences between two populations. When the benefit of the program (or the harm of not getting into it) is completely symmetric, we show that disparities between the two populations will vanish on average in the long term, although in the short term disparities will continue to arise and dissipate cyclically. Further, the time an accumulated advantage takes to dissipate can be significant, and increases as a function of the relative importance of the program in conveying benefits. Interestingly, significant disparities can arise purely due to randomness even from completely symmetric initial conditions, especially when populations are small. The introduction of even a slight asymmetry, where the group that has accumulated an advantage becomes slightly preferred, leads to a completely different outcome. In these instances, starting from completely symmetric initial conditions, disparities between groups arise stochastically and then persist over time, yielding a permanent advantage for one group. Our analysis precisely characterizes conditions under which disparities persist or diminish, with a particular focus on the role of the scarcity of available spots in the program and its effectiveness. We also present extensive simulations in a richer model that further support our theoretical results in the simpler, stylized model. Our findings are relevant for the design and implementation of algorithmic fairness interventions in similar selection processes.

cs.CY↗
arXiv2025

Who Pays the RENT? Implications of Spatial Inequality for Prediction-Based Allocation Policies

AI-powered scarce resource allocation policies rely on predictions to target either specific individuals (e.g., high-risk) or settings (e.g., neighborhoods). Recent research on individual-level targeting demonstrates conflicting results; some models show that targeting is not useful when inequality is high, while other work demonstrates potential benefits. To study and reconcile this apparent discrepancy, we develop a stylized framework based on the Mallows model to understand how the spatial distribution of inequality affects the effectiveness of door-to-door outreach policies. We introduce the RENT (Relative Efficiency of Non-Targeting) metric, which we use to assess the effectiveness of targeting approaches compared with neighborhood-based approaches in preventing tenant eviction when high-risk households are more versus less spatially concentrated. We then calibrate the model parameters to eviction court records collected in a medium-sized city in the USA. Results demonstrate considerable gains in the number of high-risk households canvassed through individually targeted policies, even in a highly segregated metro area with concentrated risks of eviction. We conclude that apparent discrepancies in the prior literature can be reconciled by considering 1) the source of deployment costs and 2) the observed versus modeled concentrations of risk. Our results inform the deployment of AI-based solutions in social service provision that account for particular applications and geographies.

cs.CY↗
arXiv2025

Street-Level AI: Are Large Language Models Ready for Real-World Judgments?

A surge of recent work explores the ethical and societal implications of large-scale AI models that make "moral" judgments. Much of this literature focuses either on alignment with human judgments through various thought experiments or on the group fairness implications of AI judgments. However, the most immediate and likely use of AI is to help or fully replace the so-called street-level bureaucrats, the individuals deciding to allocate scarce social resources or approve benefits. There is a rich history underlying how principles of local justice determine how society decides on prioritization mechanisms in such domains. In this paper, we examine how well LLM judgments align with human judgments, as well as with socially and politically determined vulnerability scoring systems currently used in the domain of homelessness resource allocation. Crucially, we use real data on those needing services (maintaining strict confidentiality by only using local large models) to perform our analyses. We find that LLM prioritizations are extremely inconsistent in several ways: internally on different runs, between different LLMs, and between LLMs and the vulnerability scoring systems. At the same time, LLMs demonstrate qualitative consistency with lay human judgments in pairwise testing. Findings call into question the readiness of current generation AI systems for naive integration in high-stakes societal decision-making.

cs.CY↗
arXiv2024

Active Geospatial Search for Efficient Tenant Eviction Outreach

Tenant evictions threaten housing stability and are a major concern for many cities. An open question concerns whether data-driven methods enhance outreach programs that target at-risk tenants to mitigate their risk of eviction. We propose a novel active geospatial search (AGS) modeling framework for this problem. AGS integrates property-level information in a search policy that identifies a sequence of rental units to canvas to both determine their eviction risk and provide support if needed. We propose a hierarchical reinforcement learning approach to learn a search policy for AGS that scales to large urban areas containing thousands of parcels, balancing exploration and exploitation and accounting for travel costs and a budget constraint. Crucially, the search policy adapts online to newly discovered information about evictions. Evaluation using eviction data for a large urban area demonstrates that the proposed framework and algorithmic approach are considerably more effective at sequentially identifying eviction cases than baseline methods.

cs.LG↗
arXiv2024

Beyond Eviction Prediction: Leveraging Local Spatiotemporal Public Records to Inform Action

There has been considerable recent interest in scoring properties on the basis of eviction risk. The success of methods for eviction prediction is typically evaluated using different measures of predictive accuracy. However, the underlying goal of such prediction is to direct appropriate assistance to households that may be at greater risk so they remain stably housed. Thus, we must ask the question of how useful such predictions are in targeting outreach efforts - informing action. In this paper, we investigate this question using a novel dataset that matches information on properties, evictions, and owners. We perform an eviction prediction task to produce risk scores and then use these risk scores to plan targeted outreach policies. We show that the risk scores are, in fact, useful, enabling a theoretical team of caseworkers to reach more eviction-prone properties in the same amount of time, compared to outreach policies that are either neighborhood-based or focus on buildings with a recent history of evictions. We also discuss the importance of neighborhood and ownership features in both risk prediction and targeted outreach.

cs.LG↗
arXiv2023

Discretionary Trees: Understanding Street-Level Bureaucracy via Machine Learning

Street-level bureaucrats interact directly with people on behalf of government agencies to perform a wide range of functions, including, for example, administering social services and policing. A key feature of street-level bureaucracy is that the civil servants, while tasked with implementing agency policy, are also granted significant discretion in how they choose to apply that policy in individual cases. Using that discretion could be beneficial, as it allows for exceptions to policies based on human interactions and evaluations, but it could also allow biases and inequities to seep into important domains of societal resource allocation. In this paper, we use machine learning techniques to understand street-level bureaucrats' behavior. We leverage a rich dataset that combines demographic and other information on households with information on which homelessness interventions they were assigned during a period when assignments were not formulaic. We find that caseworker decisions in this time are highly predictable overall, and some, but not all of this predictivity can be captured by simple decision rules. We theorize that the decisions not captured by the simple decision rules can be considered applications of caseworker discretion. These discretionary decisions are far from random in both the characteristics of such households and in terms of the outcomes of the decisions. Caseworkers typically only apply discretion to households that would be considered less vulnerable. When they do apply discretion to assign households to more intensive interventions, the marginal benefits to those households are significantly higher than would be expected if the households were chosen at random; there is no similar reduction in marginal benefit to households that are discretionarily allocated less intensive interventions, suggesting that caseworkers are improving outcomes using their knowledge.

cs.LG↗
arXiv2023

Clinical Risk Prediction Using Language Models: Benefits And Considerations

The utilization of Electronic Health Records (EHRs) for clinical risk prediction is on the rise. However, strict privacy regulations limit access to comprehensive health records, making it challenging to apply standard machine learning algorithms in practical real-world scenarios. Previous research has addressed this data limitation by incorporating medical ontologies and employing transfer learning methods. In this study, we investigate the potential of leveraging language models (LMs) as a means to incorporate supplementary domain knowledge for improving the performance of various EHR-based risk prediction tasks. Unlike applying LMs to unstructured EHR data such as clinical notes, this study focuses on using textual descriptions within structured EHR to make predictions exclusively based on that information. We extensively compare against previous approaches across various data types and sizes. We find that employing LMs to represent structured EHRs, such as diagnostic histories, leads to improved or at least comparable performance in diverse risk prediction tasks. Furthermore, LM-based approaches offer numerous advantages, including few-shot learning, the capability to handle previously unseen medical concepts, and adaptability to various medical vocabularies. Nevertheless, we underscore, through various experiments, the importance of being cautious when employing such models, as concerns regarding the reliability of LMs persist.

cs.CL↗
arXiv2023

Converging to Stability in Two-Sided Bandits: The Case of Unknown Preferences on Both Sides of a Matching Market

We study the problem of repeated two-sided matching with uncertain preferences (two-sided bandits), and no explicit communication between agents. Recent work has developed algorithms that converge to stable matchings when one side (the proposers or agents) must learn their preferences, but the preferences of the other side (the proposees or arms) are common knowledge, and the matching mechanism uses simultaneous proposals at each round. We develop new algorithms that provably converge to stable matchings for two more challenging settings: one where the arm preferences are no longer common knowledge, and a second, more general one where the arms are also uncertain about their preferences. In our algorithms, agents start with optimistic beliefs about arms' preferences and update these preferences over time. The key insight is in how to combine these beliefs about arm preferences with beliefs about the value of matching with an arm conditional on one's proposal being accepted when choosing whom to propose to.

cs.MA↗
arXiv2022

GenSyn: A Multi-stage Framework for Generating Synthetic Microdata using Macro Data Sources

Individual-level data (microdata) that characterizes a population, is essential for studying many real-world problems. However, acquiring such data is not straightforward due to cost and privacy constraints, and access is often limited to aggregated data (macro data) sources. In this study, we examine synthetic data generation as a tool to extrapolate difficult-to-obtain high-resolution data by combining information from multiple easier-to-obtain lower-resolution data sources. In particular, we introduce a framework that uses a combination of univariate and multivariate frequency tables from a given target geographical location in combination with frequency tables from other auxiliary locations to generate synthetic microdata for individuals in the target location. Our method combines the estimation of a dependency graph and conditional probabilities from the target location with the use of a Gaussian copula to leverage the available information from the auxiliary locations. We perform extensive testing on two real-world datasets and demonstrate that our approach outperforms prior approaches in preserving the overall dependency structure of the data while also satisfying the constraints defined on the different variables.

cs.LG↗
arXiv2022

Trade-offs between Group Fairness Metrics in Societal Resource Allocation

We consider social resource allocations that deliver an array of scarce supports to a diverse population. Such allocations pervade social service delivery, such as provision of homeless services, assignment of refugees to cities, among others. At issue is whether allocations are fair across sociodemographic groups and intersectional identities. Our paper shows that necessary trade-offs exist for fairness in the context of scarcity; many reasonable definitions of equitable outcomes cannot hold simultaneously except under stringent conditions. For example, defining fairness in terms of improvement over a baseline inherently conflicts with defining fairness in terms of loss compared with the best possible outcome. Moreover, we demonstrate that the fairness trade-offs stem from heterogeneity across groups in intervention responses. Administrative records on homeless service delivery offer a real-world example. Building on prior work, we measure utilities for each household as the probability of reentry into homeless services if given three homeless services. Heterogeneity in utility distributions (conditional on received services) for several sociodemographic groups (e.g. single women with children versus without children) generates divergence across fairness metrics. We argue that such heterogeneity, and thus, fairness trade-offs pervade many social policy contexts.

cs.CY↗