arXiv subjects

Juba Ziani

Publications and source records attributed to Juba Ziani.

At least 19 recordsLinked to original sources

arXiv2026

The Role of Causality in Algorithmic Recourse

Algorithmic recourse aims to provide individuals with actionable changes to improve their predicted outcomes in high-stakes classification settings, such as loan and mortgage applications. However, most existing approaches focus only on flipping a model's prediction, without accounting for whether the recommended changes lead to genuine improvement in an individual's true qualifications or merely enable strategic gaming of the classifier. Consequently, deployed recourse policies can induce behavioral responses that degrade predictive accuracy and become ineffective after model retraining. In this work, we formalize this failure mode through a causal performative framework for recourse. We model how recourse actions propagate through a structural causal model, capturing interactions among features as well as their effect on the true label. These causal responses induce a non-convex optimization problem, even under standard convex losses. We characterize conditions under which performatively stable solutions exist and can be efficiently computed via simple iterative dynamics. Our analysis reveals that recourse policies that ignore causal structure can induce large, misaligned behavioral responses, whereas causal recourse leads to stable equilibria that reduce incentives for gaming. Experiments on both semi-synthetic and real credit datasets demonstrate that our approach consistently outperforms standard empirical risk minimization while reducing the need for repeated model retraining to accommodate distribution shifts caused by strategic agent behavior.

cs.LG↗

arXiv2026

Effort Matters in Score-Based Admissions: How Retaking and Aggregation Shape Test Scores

Observed standardized test scores are the result of an endogenous process: students strategically allocate effort across multiple retake attempts to improve their outcomes. Because students differ in their ability to make these investments, the interaction between applicant strategy and institutional scoring rules---such as the widely used Single-Sitting and Superscoring policies---can disparately distort observed scores. We develop a strategic framework where students allocate effort in response to different scoring policies. We show that Superscoring---the practice of combining the best section scores across attempts---introduces systematic score inflation through order-statistic selection over noise draws. This degrades signal accuracy and amplifies wealth-based disparities by disproportionately rewarding applicants who can afford repeated testing. Conversely, Single-Sitting---which keeps the best overall score rather than section-level scores---preserves signal fidelity but excludes high-ability students who lack the resources to prepare for all subjects simultaneously. Neither rule uniformly dominates; instead, they force a structural trade-off between statistical precision and fair outcomes. Finally, to address this, we propose three algorithmic interventions which either modify how scores from multiple attempts are combined, or apply a post-hoc correction to observed scores. Using simulations calibrated to 2025 College Board data, we compare standard scoring rules against these proposed interventions.

cs.GT↗

arXiv2026

Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost

We study privately estimating the sum of $n$ user-held values in the presence of an honest-but-curious server. This motivates requiring privacy not only at data release but also throughout server-side computation. We therefore adopt the local (pure) differential privacy model, in which each user transmits a noise-perturbed value. It is well known that independent local noise typically incurs a substantial utility loss compared to the centralized model, where noise is added only after aggregation. We show that this gap is not fundamental. By carefully designing correlations among the locally added noise variables, we construct $\varepsilon$-DP mechanisms whose estimation cost matches the optimal cost achievable in the centralized setting, up to an arbitrarily small error.

cs.IT↗

arXiv2026

The Impact of Competition on Outcomes of Score-Based College Admissions

We study how the design of admissions policies affects the ability of students admitted to universities. In our model, applicants have a multi-dimensional ability, which is a combination of a "type" and a "soft skill." Universities may differ in how they evaluate quality and have differing preferences on type and soft skills. Then, university admissions rely on a single noisy aggregate signal, such as a test score, that may not fully align with the university's preferences, and a university evaluates applicants through the posterior expectations of their preference metric given the observed signal. Our main results highlight that the design of good admission policies can be counter-intuitive. Under a single university, when holding the number of qualified applicants constant, increasing the usefulness of the signal (by aligning it more closely with the university preferences) leads to a worse type and soft skill for admitted students. Further, a university cannot affect the composition of students that are strong on type versus soft skills by changing their preferences. The picture becomes even more complicated under competition between as few as two universities: self-selection effects among students admitted to both universities can lead to part of the applicant pool switching which university they prefer, even under small changes in the design of the noisy signal. This can, in particular, lead to sudden and non-monotonic loss in the quality of admitted students when changing the alignment between signal and university preferences. Further, a university can get more students by increasing their selectivity. Finally, when admissions rely on separate noisy scores for type and for soft skills, we show that universities that put more emphasis on type (respectively soft skills) end up, counter-intuitively, admitting students with higher soft skills (respectively type).

cs.GT↗

arXiv2026

Limits of Personalizing Differential Privacy Budgets

A key technical difficulty in differential privacy is selecting a privacy budget that satisfies privacy requirements while maximizing utility. A natural and well-studied workaround is to use personalized privacy budgets, which may differ across agents. In this paper, we show that personalized budgets come with major limitations and that for mean estimation, the dominant factor is not full personalization, but rather choosing the right effective privacy budget. This can be achieved through a simple thresholding operator that we describe. Compared with this thresholding baseline, the gains obtained by fully personalized mechanisms are limited. In particular, we precisely quantify the constant-factor improvement in settings with mixed private and public datasets and in private datasets with two levels of privacy requirements. We also establish upper bounds and identify regimes of maximal gain for arbitrary privacy requirements.

cs.CR↗

arXiv2026

Data Sharing with Endogenous Choices over Differential Privacy Levels

Motivated by the rapid push to decentralize sharing of data, we study whether large-scale data sharing coalitions can form in a decentralized manner under differential privacy when players have heterogeneous privacy preferences. We first consider a fully decentralized data-sharing mechanism in which each player decides whether to participate and how much privacy noise to add locally to their sensitive data before sharing. Privacy choices induce a fundamental trade-off: higher privacy lowers individual privacy costs but reduces data utility and statistical accuracy for the coalition. These choices generate externalities across players, making both participation and privacy levels strategic. Our goal is to understand which coalitions are stable, how privacy choices shape equilibrium outcomes, and how fully decentralized data-sharing compares to a centralized, socially optimal benchmark when the number of players is large. We provide a comprehensive analysis across multiple privacy-cost regimes corresponding to different attack/observation models in differential privacy, showing that full decentralization is highly inefficient in terms of both social welfare and estimator accuracy. Surprisingly, we find that a simple partially decentralized mechanism (where players still retain participation agency, but a central designer chooses a fixed privacy noise level for everyone) closes this efficiency gap down to constant factors across all privacy-cost regimes.

cs.GT↗

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

Finding a Multiple Follower Stackelberg Equilibrium: A Fully First-Order Method

In this work, we propose the first fully first-order method to compute an epsilon stationary Stackelberg equilibrium with convergence guarantees. To achieve this, we first reframe the leader follower interaction as single level constrained optimization. Second, we define the Lagrangian and show that it can approximate the leaders gradient in response to the equilibrium reached by followers with only first-order gradient evaluations. These findings suggest a fully first order algorithm that alternates between (i) approximating followers best responses through gradient descent and (ii) updating the leaders strategy via approximating the gradient using Lagrangian.

math.OC↗

arXiv2025

GLoSS: Generative Language Models with Semantic Search for Sequential Recommendation

We propose Generative Low-rank language model with Semantic Search (GLoSS), a generative recommendation framework that combines large language models with dense retrieval for sequential recommendation. Unlike prior methods such as GPT4Rec, which rely on lexical matching via BM25, GLoSS uses semantic search to retrieve relevant items beyond lexical matching. For query generation, we employ 4-bit quantized LlaMA-3 models fine-tuned with low-rank adaptation (LoRA), enabling efficient training and inference on modest hardware. We evaluate GLoSS on three real-world Amazon review datasets: Beauty, Toys, and Sports, and find that it achieves state-of-the-art performance. Compared to traditional ID-based baselines, GLoSS improves Recall@5 by 33.3%, 52.8%, and 15.2%, and NDCG@5 by 30.0%, 42.6%, and 16.1%, respectively. It also outperforms LLM-based recommenders such as P5, GPT4Rec, LlamaRec and E4SRec with Recall@5 gains of 4.3%, 22.8%, and 29.5%. Additionally, user segment evaluations show that GLoSS performs particularly well for cold-start users in the Amazon Toys and Sports datasets, and benefits from longer user histories in Amazon Beauty dataset, demonstrating robustness across different levels of interaction lengths.

cs.IR↗

arXiv2025

The Disparate Effects of Partial Information in Bayesian Strategic Learning

We study how partial information about scoring rules affects fairness in strategic learning settings. In strategic learning, a learner deploys a scoring rule, and agents respond strategically by modifying their features -- at some cost -- to improve their outcomes. However, in our work, agents do not observe the scoring rule directly; instead, they receive a noisy signal of said rule. We consider two different agent models: (i) naive agents, who take the noisy signal at face value, and (ii) Bayesian agents, who update a prior belief based on the signal. Our goal is to understand how disparities in outcomes arise between groups that differ in their costs of feature modification, and how these disparities vary with the level of transparency of the learner's rule. For naive agents, we show that utility disparities can grow unboundedly with noise, and that the group with lower costs can, perhaps counter-intuitively, be disproportionately harmed under limited transparency. In contrast, for Bayesian agents, disparities remain bounded. We provide a full characterization of disparities across groups as a function of the level of transparency and show that they can vary non-monotonically with noise; in particular, disparities are often minimized at intermediate levels of transparency. Finally, we extend our analysis to settings where groups differ not only in cost, but also in prior beliefs, and study how this asymmetry influences fairness.

cs.GT↗

arXiv2025

KL-regularization Itself is Differentially Private in Bandits and RLHF

Differential Privacy (DP) provides a rigorous framework for privacy, ensuring the outputs of data-driven algorithms remain statistically indistinguishable across datasets that differ in a single entry. While guaranteeing DP generally requires explicitly injecting noise either to the algorithm itself or to its outputs, the intrinsic randomness of existing algorithms presents an opportunity to achieve DP ``for free''. In this work, we explore the role of regularization in achieving DP across three different decision-making problems: multi-armed bandits, linear contextual bandits, and reinforcement learning from human feedback (RLHF), in offline data settings. We show that adding KL-regularization to the learning objective (a common approach in optimization algorithms) makes the action sampled from the resulting stochastic policy itself differentially private. This offers a new route to privacy guarantees without additional noise injection, while also preserving the inherent advantage of regularization in enhancing performance.

cs.LG↗

arXiv2025

Optimal Allocation of Privacy Budget on Hierarchical Data Release

Releasing useful information from datasets with hierarchical structures while preserving individual privacy presents a significant challenge. Standard privacy-preserving mechanisms, and in particular Differential Privacy, often require careful allocation of a finite privacy budget across different levels and components of the hierarchy. Sub-optimal allocation can lead to either excessive noise, rendering the data useless, or to insufficient protections for sensitive information. This paper addresses the critical problem of optimal privacy budget allocation for hierarchical data release. It formulates this challenge as a constrained optimization problem, aiming to maximize data utility subject to a total privacy budget while considering the inherent trade-offs between data granularity and privacy loss. The proposed approach is supported by theoretical analysis and validated through comprehensive experiments on real hierarchical datasets. These experiments demonstrate that optimal privacy budget allocation significantly enhances the utility of the released data and improves the performance of downstream tasks.

cs.CR↗

arXiv2025

Last-iterate Convergence for Symmetric, General-sum, $2 \times 2$ Games Under The Exponential Weights Dynamic

We conduct a comprehensive analysis of the discrete-time exponential-weights dynamic with a constant step size on all general-sum and symmetric $2 \times 2$ normal-form games, i.e. games with $2$ pure strategies per player, and where the ensuing payoff tuple is of the form $(A,A^\top)$ (where $A$ is the $2 \times 2$ payoff matrix corresponding to the first player). Such symmetric games commonly arise in real-world interactions between 'symmetric" agents who have identically defined utility functions -- such as Bertrand competition and multi-agent performative prediction, and display a rich multiplicity of equilibria despite the seemingly simple setting. Somewhat surprisingly, we show through a first-principles analysis that the exponential weights dynamic, which is popular in online learning, converges in the last iterate for such games regardless of initialization with an appropriately chosen step size. For certain games and/or initializations, we further show that the convergence rate is in fact exponential and holds for any step size. We illustrate our theory with extensive simulations and applications to the aforementioned game-theoretic interactions. In the case of multi-agent performative prediction, we formulate a new "mortgage competition" game between lenders (i.e. banks) who interact with a population of customers, and show that it fits into our framework.

cs.GT↗

arXiv2025

Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty

We study strategic classification in binary decision-making settings where agents can modify their features in order to improve their classification outcomes. Importantly, our work considers the causal structure across different features, acknowledging that effort in a given feature may affect other features. The main goal of our work is to understand \emph{when and how much agent effort is invested towards desirable features}, and how this is influenced by the deployed classifier, the causal structure of the agent's features, their ability to modify them, and the information available to the agent about the classifier and the feature causal graph. In the complete information case, when agents know the classifier and the causal structure of the problem, we derive conditions ensuring that rational agents focus on features favored by the principal. We show that designing classifiers to induce desirable behavior is generally non-convex, though tractable in special cases. We also extend our analysis to settings where agents have incomplete information about the classifier or the causal graph. While optimal effort selection is again a non-convex problem under general uncertainty, we highlight special cases of partial uncertainty where this selection problem becomes tractable. Our results indicate that uncertainty drives agents to favor features with higher expected importance and lower variance, potentially misaligning with principal preferences. Finally, numerical experiments based on a cardiovascular disease risk study illustrate how to incentivize desirable modifications under uncertainty.

cs.GT↗

arXiv2025

The Cost of Balanced Training-Data Production in an Online Data Market

Many ethical issues in machine learning are connected to the training data. Online data markets are an important source of training data, facilitating both production and distribution. Recently, a trend has emerged of for-profit "ethical" participants in online data markets. This trend raises a fascinating question: Can online data markets sustainably and efficiently address ethical issues in the broader machine-learning economy? In this work, we study this question in a stylized model of an online data market. We investigate the effects of intervening in the data market to achieve balanced training-data production. The model reveals the crucial role of market conditions. In small and emerging markets, an intervention can drive the data producers out of the market, so that the cost of fairness is maximal. Yet, in large and established markets, the cost of fairness can vanish (as a fraction of overall welfare) as the market grows. Our results suggest that "ethical" online data markets can be economically feasible under favorable market conditions, and motivate more models to consider the role of data production and distribution in mediating the impacts of ethical interventions.

cs.GT↗

arXiv2025

When Should a Principal Delegate to an Agent in Selection Processes?

Decision-makers in high-stakes selection processes often face a fundamental choice: whether to make decisions themselves or to delegate authority to another entity whose incentives may only be partially aligned with their own. Such delegation arises naturally in settings like graduate admissions, hiring, or promotion, where a principal (e.g. a professor or worker) either reviews applicants personally or decisions are delegated to an agent (e.g. a committee or boss) that evaluates applicants efficiently, but according to a potentially misaligned objective. We study this trade-off in a stylized selection model with noisy signals. The principal incurs a cost for selecting applicants, but can evaluate applicants based on their fit with a project, team, workplace, etc. In contrast, the agent evaluates applicants solely on the basis of a signal that correlates with the principal's metric, but this comes at no cost to the principal. Our goal is to characterize when delegation is beneficial versus when decision-making should remain with the principal. We compare these regimes along three dimensions: (i) the principal's utility, (ii) the quality of the selected applicants according to the principal's metric, and (iii) the fairness of selection outcomes under disparate signal qualities.

cs.CY↗

arXiv2024

Differential Privacy Overview and Fundamental Techniques

This chapter is meant to be part of the book "Differential Privacy in Artificial Intelligence: From Theory to Practice" and provides an introduction to Differential Privacy. It starts by illustrating various attempts to protect data privacy, emphasizing where and why they failed, and providing the key desiderata of a robust privacy definition. It then defines the key actors, tasks, and scopes that make up the domain of privacy-preserving data analysis. Following that, it formalizes the definition of Differential Privacy and its inherent properties, including composition, post-processing immunity, and group privacy. The chapter also reviews the basic techniques and mechanisms commonly used to implement Differential Privacy in its pure and approximate forms.

cs.CR↗

arXiv2024

Algorithmic Collusion Without Threats

There has been substantial recent concern that pricing algorithms might learn to ``collude.'' Supra-competitive prices can emerge as a Nash equilibrium of repeated pricing games, in which sellers play strategies which threaten to punish their competitors who refuse to support high prices, and these strategies can be automatically learned. In fact, a standard economic intuition is that supra-competitive prices emerge from either the use of threats, or a failure of one party to optimize their payoff. Is this intuition correct? Would preventing threats in algorithmic decision-making prevent supra-competitive prices when sellers are optimizing for their own revenue? No. We show that supra-competitive prices can emerge even when both players are using algorithms which do not encode threats, and which optimize for their own revenue. We study sequential pricing games in which a first mover deploys an algorithm and then a second mover optimizes within the resulting environment. We show that if the first mover deploys any algorithm with a no-regret guarantee, and then the second mover even approximately optimizes within this now static environment, monopoly-like prices arise. The result holds for any no-regret learning algorithm deployed by the first mover and for any pricing policy of the second mover that obtains them profit at least as high as a random pricing would -- and hence the result applies even when the second mover is optimizing only within a space of non-responsive pricing distributions which are incapable of encoding threats. In fact, there exists a set of strategies, neither of which explicitly encode threats that form a Nash equilibrium of the simultaneous pricing game in algorithm space, and lead to near monopoly prices. This suggests that the definition of ``algorithmic collusion'' may need to be expanded, to include strategies without explicitly encoded threats.

cs.GT↗