arXiv subjects

Ganesh Ghalme

Publications and source records attributed to Ganesh Ghalme.

At least 19 recordsLinked to original sources

arXiv2026

Fair Stable Matching: A Nash Social Welfare Approach

While traditional stable matching algorithms, such as the Gale-Shapley algorithm, prioritize stability, they may fall short of achieving equitable outcomes among participants. We study the role of \emph{Nash social welfare} (NSW) as a fairness objective in the classic \emph{stable marriage problem}. We develop \texttt{SNSW-Alg} that finds a stable matching that maximizes Nash social welfare under rank-induced utilities in $\tilde{\mathcal{O}}(n^4)$ time, where $n$ is the number of men or women. We demonstrate that \texttt{SNSW-Alg} balances equity while preserving stability. We empirically evaluate our methods across diverse preference distributions, demonstrating significant gains in fairness without substantial losses in other key measures such as regret, egalitarian criterion, and sex equality. Our findings suggest that the stable matching produced by \texttt{SNSW-Alg} is statistically Pareto-undominated by stable matchings based on other fairness measures - regret, egalitarian, and sex equality. This study offers compelling insights for designing fair-stable matching.

cs.GT↗

arXiv2026

Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents

We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle that governance should control an AI agent through resource allocation so as to make authorization self enforcing via compute budgets. The mechanism seeks to establish the Safe AI paradigm that compute is an effective governance lever. We situate our work as a compliance or commons overlay on a deployer. One governance period is an extensive form game in which verified human stakeholders arrive sequentially and contribute, on a provision or a rejection market, in a governance currency that is deliberately distinct from the agents compute. A funding aggregator turns raw contributions into breadth weighted effective supports - a two threshold gate with hysteresis converts net support into a binary authorization that, through a coupling map bounded by an exogenously certified safety ceiling, releases a metered compute budget - realized in hardware as a signed compute license so that the decision is self-enforcing. We characterize the class of agents the mechanism can govern and isolate manipulation of the governing electorate by the governed agent as the central open problem. We also introduce several challenges addressing manipulation of governing electorate by the governed agents.

cs.GT↗

arXiv2026

Multi-Sender Bayesian Persuasion with Imperfect Information

We study a multi-sender Bayesian persuasion problem with one receiver and several strategic senders. The underlying ground state has multiple components, each privately observed by a different sender, while the receiver holds a common prior over the joint state space. Senders simultaneously choose signaling policies, and the receiver takes an action based on the posterior induced by the signals; each is sampled independently from the sender's signaling policy. We analyze the game induced by the receiver's straightforward policy, which selects a receiver-optimal action at every posterior. In particular, we characterize the senders' best responses under the straightforward policy and identify conditions on the prior that induce a fully informative equilibrium; i.e., truthfully reporting the ground truth is an equilibrium strategy for every sender. These conditions capture cases in which senders' incentives are sufficiently aligned to enable full revelation without additional commitment from the receiver. The important contribution of this paper is to analyze games induced by a more general (possibly randomized) class of action policies that the receiver commits to before senders choose their signaling strategies. We show that this commitment power fundamentally changes the problem. In particular, we show that for any prior over the joint state space, the receiver can construct action policies that maximize her payoff while ensuring a fully informative equilibrium.

cs.GT↗

arXiv2026

Linear Strategic Classification with Endogenous Improvements

Strategic classification studies settings in which agents respond to a deployed classifier by modifying observable features at a cost. Classical models typically treat such responses as cosmetic: features may change, but true labels remain fixed. We study an improvement-aware variant in which strategic responses can induce genuine changes in outcome-relevant features. Agents choose post-deployment feature vectors strategically, and labels are then generated according to a stable conditional outcome law that preserves the relationship between features and outcomes. We formalize this problem for linear classifiers under a single-index qualification model and linear-decomposable costs. We show that the strategic-optimal classifier is obtained by a parallel shift of the Bayes-optimal decision boundary, and that it provides a better surrogate for the improvement-aware objective than the Bayes classifier. Since improvement-aware learning requires post-deployment labels, which are typically unavailable before deployment, we provide PAC-style guar- antees under an oracle model, propose a practical plug-in algorithm, establish its generalization bound, and evaluate it on synthetic and real-world datasets.

cs.LG↗

arXiv2026

Lipschitz Dueling Bandits over Continuous Action Spaces

We study for the first time, stochastic dueling bandits over continuous action spaces with Lipschitz structure, where feedback is purely comparative. While dueling bandits and Lipschitz bandits have been studied separately, their combination has remained unexplored. We propose the first algorithm for Lipschitz dueling bandits, using round-based exploration and recursive region elimination guided by an adaptive reference arm. We develop new analytical tools for relative feedback and prove a regret bound of $\tilde O\left(T^{\frac{d_z+1}{d_z+2}}\right)$, where $d_z$ is the zooming dimension of the near-optimal region. Further, our algorithm takes only logarithmic space in terms of the total time horizon, best achievable by any bandit algorithm over a continuous action space.

cs.LG↗

arXiv2025

On Condorcet's Jury Theorem with Abstention

The well-known Condorcet Jury Theorem states that, under majority rule, the better of two alternatives is chosen with probability approaching one as the population grows. We study an asymmetric setting where voters face varying participation costs and share a possibly heuristic belief about their pivotality (ability to influence the outcome). In a costly voting setup where voters abstain if their participation cost is greater than their pivotality estimate, we identify a single property of the heuristic belief -- weakly vanishing pivotality -- that gives rise to multiple stable equilibria in which elections are nearly tied. In contrast, strongly vanishing pivotality (as in the standard Calculus of Voting model) yields a unique, trivial equilibrium where only zero-cost voters participate as the population grows. We then characterize when nontrivial equilibria satisfy a version of the Jury Theorem: below a sharp threshold, the majority-preferred candidate wins with probability approaching one; above it, both candidates either win with equal probability.

cs.GT↗

arXiv2025

Multi-agent Multi-armed Bandits with Minimum Reward Guarantee Fairness

We investigate the problem of maximizing social welfare while ensuring fairness in a multi-agent multi-armed bandit (MA-MAB) setting. In this problem, a centralized decision-maker takes actions over time, generating random rewards for various agents. Our goal is to maximize the sum of expected cumulative rewards, a.k.a. social welfare, while ensuring that each agent receives an expected reward that is at least a constant fraction of the maximum possible expected reward. Our proposed algorithm, RewardFairUCB, leverages the Upper Confidence Bound (UCB) technique to achieve sublinear regret bounds for both fairness and social welfare. The fairness regret measures the positive difference between the minimum reward guarantee and the expected reward of a given policy, whereas the social welfare regret measures the difference between the social welfare of the optimal fair policy and that of the given policy. We show that RewardFairUCB algorithm achieves instance-independent social welfare regret guarantees of $\tilde{O}(T^{1/2})$ and a fairness regret upper bound of $\tilde{O}(T^{3/4})$. We also give the lower bound of $Ω(\sqrt{T})$ for both social welfare and fairness regret. We evaluate RewardFairUCB's performance against various baseline and heuristic algorithms using simulated data and real world data, highlighting trade-offs between fairness and social welfare regrets.

cs.LG↗

arXiv2024

Condorcet's Jury Theorem with Abstention

The well-known Condorcet's Jury theorem posits that the majority rule selects the best alternative among two available options with probability one, as the population size increases to infinity. We study this result under an asymmetric two-candidate setup, where supporters of both candidates may have different participation costs. When the decision to abstain is fully rational i.e., when the vote pivotality is the probability of a tie, the only equilibrium outcome is a trivial equilibrium where all voters except those with zero voting cost, abstain. We propose and analyze a more practical, boundedly rational model where voters overestimate their pivotality, and show that under this model, non-trivial equilibria emerge where the winning probability of both candidates is bounded away from one. We show that when the pivotality estimate strongly depends on the margin of victory, victory is not assured to any candidate in any non-trivial equilibrium, regardless of population size and in contrast to Condorcet's assertion. Whereas, under a weak dependence on margin, Condorcet's Jury theorem is restored.

cs.GT↗

arXiv2024

Simultaneously Achieving Group Exposure Fairness and Within-Group Meritocracy in Stochastic Bandits

Existing approaches to fairness in stochastic multi-armed bandits (MAB) primarily focus on exposure guarantee to individual arms. When arms are naturally grouped by certain attribute(s), we propose Bi-Level Fairness, which considers two levels of fairness. At the first level, Bi-Level Fairness guarantees a certain minimum exposure to each group. To address the unbalanced allocation of pulls to individual arms within a group, we consider meritocratic fairness at the second level, which ensures that each arm is pulled according to its merit within the group. Our work shows that we can adapt a UCB-based algorithm to achieve a Bi-Level Fairness by providing (i) anytime Group Exposure Fairness guarantees and (ii) ensuring individual-level Meritocratic Fairness within each group. We first show that one can decompose regret bounds into two components: (a) regret due to anytime group exposure fairness and (b) regret due to meritocratic fairness within each group. Our proposed algorithm BF-UCB balances these two regrets optimally to achieve the upper bound of $O(\sqrt{T})$ on regret; $T$ being the stopping time. With the help of simulated experiments, we further show that BF-UCB achieves sub-linear regret; provides better group and individual exposure guarantees compared to existing algorithms; and does not result in a significant drop in reward with respect to UCB algorithm, which does not impose any fairness constraint.

cs.LG↗

arXiv2023

Designing Fair, Cost-optimal Auctions based on Deep Learning for Procuring Agricultural Inputs through Farmer Collectives

Procuring agricultural inputs (agri-inputs for short) such as seeds, fertilizers, and pesticides, at desired quality levels and at affordable cost, forms a critical component of agricultural input operations. This is a particularly challenging problem being faced by small and marginal farmers in any emerging economy. Farmer collectives (FCs), which are cooperative societies of farmers, offer an excellent prospect for enabling cost-effective procurement of inputs with assured quality to the farmers. In this paper, our objective is to design sound, explainable mechanisms by which an FC will be able to procure agri-inputs in bulk and distribute the inputs procured to the individual farmers who are members of the FC. In the methodology proposed here, an FC engages qualified suppliers in a competitive, volume discount procurement auction in which the suppliers specify price discounts based on volumes supplied. The desiderata of properties for such an auction include: minimization of the total cost of procurement; incentive compatibility; individual rationality; fairness; and other business constraints. An auction satisfying all these properties is analytically infeasible and a key contribution of this paper is to develop a deep learning based approach to design such an auction. We use two realistic, stylized case studies from chili seeds procurement and a popular pesticide procurement to demonstrate the efficacy of these auctions.

cs.GT↗

arXiv2022

Envy-Free Cake Cutting with Graph Constraints

We study the classic problem of fairly dividing a heterogeneous and divisible resource -- represented by a cake, $[0,1]$ -- among $n$ agents. This work considers an interesting variant of the problem where agents are embedded on a graph. The graphical constraint entails that each agent evaluates her allocated share only against her neighbor's share. Given a graph, the goal is to efficiently find a locally envy-free allocation where every agent values her share to be at least as much as any of her neighbor's share. The best known algorithm (by Aziz and Mackenzie) for finding envy-free cake divisions has a hyper-exponential query complexity. One of the key technical contributions of this work is to identify a non-trivial graph structure -- tree graphs with depth at-most two (Depth2Tree) -- on $n$ agents that admits a query efficient cake-cutting protocol (under the Robertson-Webb query model). In particular, we develop a discrete protocol that finds a locally envy-free allocation among $n$ agents on depth-two trees with at-most $O(n^3 \log(n))$ cuts on the cake. For the special case of Depth2Tree where every non-root agent is connected to at-most two agents (2-Star), we show that $O(n^2)$ queries suffice. We complement our algorithmic results with establishing a lower bound of $Ω(n^2)$ (evaluation) queries for finding a locally envy-free allocation among $n$ agents on a 1-Star graph (under the assumption that the root agent partitions the cake into $n$ connected pieces).

cs.GT↗

arXiv2022

A Discrete and Bounded Locally Envy-Free Cake Cutting Protocol on Trees

We study the classic problem of \emph{fairly} dividing a heterogeneous and divisible resource -- modeled as a line segment $[0,1]$ and typically called as a \emph{cake} -- among $n$ agents. This work considers an interesting variant of the problem where agents are embedded on a graph. The graphical constraint entails that each agent evaluates her allocated share only against her neighbors' share. Given a graph, the goal is to efficiently find a \emph{locally envy-free} allocation where every agent values her share of the cake to be at least as much as that of any of her neighbors' share. The most significant contribution of this work is a bounded protocol that finds a locally envy-free allocation among $n$ agents on a tree graph using $n^{O(n)}$ queries under the standard Robertson-Webb (RW) query model. The query complexity of our proposed protocol, though exponential, significantly improves the currently best known hyper-exponential query complexity bound of Aziz and Mackenzie [AM16] for complete graphs. In particular, we also show that if the underlying tree graph has a depth of at most two, one can find a locally envy-free allocation with $O(n^4 \log n)$ RW queries. This is the first and the only known locally envy-free cake cutting protocol with polynomial query complexity for a non-trivial graph structure. Interestingly, our discrete protocols are simple and easy to understand, as opposed to highly involved protocol of [AM16]. This simplicity can be attributed to their recursive nature and the use of a single agent as a designated \emph{cutter}. We believe that these results will help us improve our algorithmic understanding of the arguably challenging problem of envy-free cake-cutting by uncovering the bottlenecks in its query complexity and its relation to the underlying graph structures.

cs.GT↗

arXiv2022

Mitigating Disparity while Maximizing Reward: Tight Anytime Guarantee for Improving Bandits

We study the Improving Multi-Armed Bandit (IMAB) problem, where the reward obtained from an arm increases with the number of pulls it receives. This model provides an elegant abstraction for many real-world problems in domains such as education and employment, where decisions about the distribution of opportunities can affect the future capabilities of communities and the disparity between them. A decision-maker in such settings must consider the impact of her decisions on future rewards in addition to the standard objective of maximizing her cumulative reward at any time. In many of these applications, the time horizon is unknown to the decision-maker beforehand, which motivates the study of the IMAB problem in the technically more challenging horizon-unaware setting. We study the tension that arises between two seemingly conflicting objectives in the horizon-unaware setting: a) maximizing the cumulative reward at any time based on current rewards of the arms, and b) ensuring that arms with better long-term rewards get sufficient opportunities even if they initially have low rewards. We show that, surprisingly, the two objectives are aligned with each other in this setting. Our main contribution is an anytime algorithm for the IMAB problem that achieves the best possible cumulative reward while ensuring that the arms reach their true potential given sufficient time. Our algorithm mitigates the initial disparity due to lack of opportunity and continues pulling an arm till it stops improving. We prove the optimality of our algorithm by showing that a) any algorithm for the IMAB problem, no matter how utilitarian, must suffer $Ω(T)$ policy regret and $Ω(k)$ competitive ratio with respect to the optimal offline policy, and b) the competitive ratio of our algorithm is $O(k)$.

cs.LG↗

arXiv2022

Efficient Algorithms For Fair Clustering with a New Fairness Notion

We revisit the problem of fair clustering, first introduced by Chierichetti et al., that requires each protected attribute to have approximately equal representation in every cluster; i.e., a balance property. Existing solutions to fair clustering are either not scalable or do not achieve an optimal trade-off between clustering objective and fairness. In this paper, we propose a new notion of fairness, which we call $tau$-fair fairness, that strictly generalizes the balance property and enables a fine-grained efficiency vs. fairness trade-off. Furthermore, we show that simple greedy round-robin based algorithms achieve this trade-off efficiently. Under a more general setting of multi-valued protected attributes, we rigorously analyze the theoretical properties of the our algorithms. Our experimental results suggest that the proposed solution outperforms all the state-of-the-art algorithms and works exceptionally well even for a large number of clusters.

cs.LG↗

arXiv2022

Strategic Representation

Humans have come to rely on machines for reducing excessive information to manageable representations. But this reliance can be abused -- strategic machines might craft representations that manipulate their users. How can a user make good choices based on strategic representations? We formalize this as a learning problem, and pursue algorithms for decision-making that are robust to manipulation. In our main setting of interest, the system represents attributes of an item to the user, who then decides whether or not to consume. We model this interaction through the lens of strategic classification (Hardt et al. 2016), reversed: the user, who learns, plays first; and the system, which responds, plays second. The system must respond with representations that reveal `nothing but the truth' but need not reveal the entire truth. Thus, the user faces the problem of learning set functions under strategic subset selection, which presents distinct algorithmic and statistical challenges. Our main result is a learning algorithm that minimizes error despite strategic representations, and our theoretical analysis sheds light on the trade-off between learning effort and susceptibility to manipulation.

cs.LG↗

arXiv2022

Individual Fairness in Feature-Based Pricing for Monopoly Markets

We study fairness in the context of feature-based price discrimination in monopoly markets. We propose a new notion of individual fairness, namely, α-fairness, which guarantees that individuals with similar features face similar prices. First, we study discrete valuation space and give an analytical solution for optimal fair feature-based pricing. We show that the cost of fair pricing is defined as the ratio of expected revenue in an optimal feature-based pricing to the expected revenue in an optimal fair feature-based pricing (CoF) can be arbitrarily large in general. When the revenue function is continuous and concave with respect to the prices, we show that one can achieve CoF strictly less than 2, irrespective of the model parameters. Finally, we provide an algorithm to compute fair feature-based pricing strategy that achieves this CoF.

cs.GT↗

arXiv2022

Long-Term Resource Allocation Fairness in Average Markov Decision Process (AMDP) Environment

Fairness has emerged as an important concern in automated decision-making in recent years, especially when these decisions affect human welfare. In this work, we study fairness in temporally extended decision-making settings, specifically those formulated as Markov Decision Processes (MDPs). Our proposed notion of fairness ensures that each state's long-term visitation frequency is at least a specified fraction. This quota-based notion of fairness is natural in many resource-allocation settings where the dynamics of a single resource being allocated is governed by an MDP and the distribution of the shared resource is captured by its state-visitation frequency. In an average-reward MDP (AMDP) setting, we formulate the problem as a bilinear saddle point program and, for a generative model, solve it using a Stochastic Mirror Descent (SMD) based algorithm. The proposed solution guarantees a simultaneous approximation on the expected average-reward and fairness requirement. We give sample complexity bounds for the proposed algorithm and validate our theoretical results with experiments on simulated data.

cs.AI↗

arXiv2021

Strategic Classification in the Dark

Strategic classification studies the interaction between a classification rule and the strategic agents it governs. Under the assumption that the classifier is known, rational agents respond to it by manipulating their features. However, in many real-life scenarios of high-stake classification (e.g., credit scoring), the classifier is not revealed to the agents, which leads agents to attempt to learn the classifier and game it too. In this paper we generalize the strategic classification model to such scenarios. We define the price of opacity as the difference in prediction error between opaque and transparent strategy-robust classifiers, characterize it, and give a sufficient condition for this price to be strictly positive, in which case transparency is the recommended policy. Our experiments show how Hardt et al.'s robust classifier is affected by keeping agents in the dark.

cs.LG↗