arXiv subjects

MohammadTaghi Hajiaghayi

Publications and source records attributed to MohammadTaghi Hajiaghayi.

At least 37 records · Page 2Linked to original sources

arXiv2026

Single-Sample Bilateral Trade with a Broker

We initiate the study of single-sample bilateral trade with a broker, drawing an analogy to the setting of single-sample bilateral trade without a broker considered in Babaioff et al. (2020) and Cai and Wu (2023). Our model captures the three-sided interaction in which a broker mediates trade between a buyer and seller, each described by a valuation distribution from which a single sample can be drawn. We consider two settings in particular: one where the valuation distributions of the buyer and seller are identical and one where the valuation distributions are stochastically ordered. We analyze simple mechanisms that rely only on a single sample from each agent's distribution and show that these mechanisms achieve constant-factor approximations to the first-best gains-from-trade (GFT), first-best social welfare (SW), and optimal profit under the standard monotone-hazard-rate assumption. We then complement these results with matching or nearly matching upper bounds on the GFT and SW of our mechanisms. Notably, in both settings, we observe fairly small losses in the approximation factors to the first-best GFT and first-best SW due to the existence of the broker (benchmarked against the corresponding approximation factors in the setting without a broker). Furthermore, our results stand in stark contrast to those of Hajiaghayi et al. (2025), who show inapproximability results under a strategic broker with full distributional knowledge. Our results provide insight into the design of data-efficient brokerage mechanisms for online marketplaces and decentralized trading platforms, where intermediaries must facilitate trade under severe informational constraints. They highlight how even minimal data can enable robust and incentive-compatible brokerage in uncertain markets for both the broker and the market participants.

cs.GT↗

arXiv2026

Active Learning for Decision Trees with Provable Guarantees

This paper advances the theoretical understanding of active learning label complexity for decision trees as binary classifiers. We make two main contributions. First, we provide the first analysis of the disagreement coefficient for decision trees-a key parameter governing active learning label complexity. Our analysis holds under two natural assumptions required for achieving polylogarithmic label complexity, (i) each root-to-leaf path queries distinct feature dimensions, and (ii) the input data has a regular, grid-like structure. We show these assumptions are essential, as relaxing them leads to polynomial label complexity. Second, we present the first general active learning algorithm for binary classification that achieves a multiplicative error guarantee, producing a $(1+ε)$-approximate classifier. By combining these results, we design an active learning algorithm for decision trees that uses only a polylogarithmic number of label queries in the dataset size, under the stated assumptions. Finally, we establish a label complexity lower bound, showing our algorithm's dependence on the error tolerance $ε$ is close to optimal.

cs.LG↗

arXiv2025

Dynamic Diameter in High-Dimensions against Adaptive Adversary and Beyond

In this paper, we study the fundamental problems of maintaining the diameter and a $k$-center clustering of a dynamic point set $P \subset \mathbb{R}^d$, where points may be inserted or deleted over time and the ambient dimension $d$ is not constant and may be high. Our focus is on designing algorithms that remain effective even in the presence of an adaptive adversary -- an adversary that, at any time $t$, knows the entire history of the algorithm's outputs as well as all the random bits used by the algorithm up to that point. We present a fully dynamic algorithm that maintains a $2$-approximate diameter with a worst-case update time of $\text{poly}(d, \log n)$, where $n$ is the length of the stream. Our result is achieved by identifying a robust representative of the dataset that requires infrequent updates, combined with a careful deamortization. To the best of our knowledge, this is the first efficient fully-dynamic algorithm for diameter in high dimensions that simultaneously achieves a 2-approximation guarantee and robustness against an adaptive adversary. We also give an improved dynamic $(4+ε)$-approximation algorithm for the $k$-center problem, also resilient to an adaptive adversary. Our clustering algorithm achieves an amortized update time of $k^{2.5} d \cdot \text{poly}(ε^{-1}, \log n)$, improving upon the amortized update time of $k^6 d \cdot \text{poly}(ε^{-1}, \log n)$ by Biabani et al. [NeurIPS'24].

cs.DS↗

arXiv2025

Dynamic Dyck and Tree Edit Distance: Decompositions and Reductions to String Edit Distance

We present the first dynamic algorithms for Dyck and tree edit distances with subpolynomial update times. Dyck edit distance measures how far a parenthesis string is from a well-parenthesized expression, while tree edit distance quantifies the minimum number of node insertions, deletions, and substitutions required to transform one rooted, ordered, labeled tree into another. Despite extensive study, no prior work has addressed efficient dynamic algorithms for these problems, which naturally arise in evolving structured data such as LaTeX documents, JSON or XML files, and RNA secondary structures. Our main contribution is a set of reductions and decompositions that transform Dyck and tree edit distance instances into efficiently maintainable string edit distance instances, which can be approximated within a $n^{o(1)}$ factor in $n^{o(1)}$ update time. For Dyck edit distance, our reduction incurs only polylogarithmic overheads in approximation and update time, yielding an $n^{o(1)}$-approximation with $n^{o(1)}$ updates. For tree edit distance, we introduce a new static reduction that improves the best-known approximation ratio from $n^{3/4}$ to $\tilde{O}(\sqrt{n})$ and removes the restriction to constant-degree trees. Extending this reduction dynamically achieves $n^{1/2+o(1)}$ approximation with $n^{o(1)}$ update time. A key component is a dynamic maintenance algorithm for history-independent heavy-light decompositions, of independent interest. We also provide a novel static and dynamic decomposition achieving an $O(k \log n)$-approximation when the tree edit distance is at most $k$. Combined with the trivial bound $k \le n$, this yields a dynamic deterministic $O(\sqrt{n \log n})$-approximation. In the static setting, our algorithm runs in near-linear time; dynamically, it requires only polylogarithmic updates, improving on prior linear-time static $O(\sqrt{n})$-approximation.

cs.DS↗

arXiv2025

How Bad Is Forming Your Own Multidimensional Opinion?

Understanding the formation of opinions on interconnected topics within social networks is of significant importance. It offers insights into collective behavior and decision-making, with applications in Graph Neural Networks. Existing models propose that individuals form opinions based on a weighted average of their peers' opinions and their own beliefs. This averaging process, viewed as a best-response game, can be seen as an individual minimizing disagreements with peers, defined by a quadratic penalty, leading to an equilibrium. Bindel, Kleinberg, and Oren (FOCS 2011) provided tight bounds on the "price of anarchy" defined as the maximum overall disagreement at equilibrium relative to a social optimum. Bhawalkar, Gollapudi, and Munagala (STOC 2013) generalized the penalty function to non-quadratic penalties and provided tight bounds on the price of anarchy. When considering multiple topics, an individual's opinions can be represented as a vector. Parsegov, Proskurnikov, Tempo, and Friedkin (2016) proposed a multidimensional model using the weighted averaging process, but with constant interdependencies between topics. However, the question of the price of anarchy for this model remained open. We address this by providing tight bounds on the multidimensional model, while also generalizing it to more complex interdependencies. Following the work of Bhawalkar, Gollapudi, and Munagala, we provide tight bounds on the price of anarchy under non-quadratic penalties. Surprisingly, these bounds match the scalar model. We further demonstrate that the bounds remain unchanged even when adding another layer of complexity, involving groups of individuals minimizing their overall internal and external disagreement penalty, a common occurrence in real-life scenarios.

cs.GT↗

arXiv2025

Less is More: Adaptive Coverage for Synthetic Training Data

Synthetic training data generation with Large Language Models (LLMs) like Google's Gemma and OpenAI's GPT offer a promising solution to the challenge of obtaining large, labeled datasets for training classifiers. When rapid model deployment is critical, such as in classifying emerging social media trends or combating new forms of online abuse tied to current events, the ability to generate training data is invaluable. While prior research has examined the comparability of synthetic data to human-labeled data, this study introduces a novel sampling algorithm, based on the maximum coverage problem, to select a representative subset from a synthetically generated dataset. Our results demonstrate that training a classifier on this contextually sampled subset achieves superior performance compared to training on the entire dataset. This "less is more" approach not only improves model accuracy but also reduces the volume of data required, leading to potentially more efficient model fine-tuning.

cs.LG↗

arXiv2025

Ad Auctions for LLMs via Retrieval Augmented Generation

In the field of computational advertising, the integration of ads into the outputs of large language models (LLMs) presents an opportunity to support these services without compromising content integrity. This paper introduces novel auction mechanisms for ad allocation and pricing within the textual outputs of LLMs, leveraging retrieval-augmented generation (RAG). We propose a segment auction where an ad is probabilistically retrieved for each discourse segment (paragraph, section, or entire output) according to its bid and relevance, following the RAG framework, and priced according to competing bids. We show that our auction maximizes logarithmic social welfare, a new notion of welfare that balances allocation efficiency and fairness, and we characterize the associated incentive-compatible pricing rule. These results are extended to multi-ad allocation per segment. An empirical evaluation validates the feasibility and effectiveness of our approach over several ad auction scenarios, and exhibits inherent tradeoffs in metrics as we allow the LLM more flexibility to allocate ads.

cs.GT↗

arXiv2025

Prize-Collecting Forest with Submodular Penalties: Improved Approximation

Constrained forest problems form a class of graph problems where specific connectivity requirements for certain cuts within the graph must be satisfied by selecting the minimum-cost set of edges. The prize-collecting version of these problems introduces flexibility by allowing penalties to be paid to ignore some connectivity requirements. Goemans and Williamson introduced a general technique and developed a 2-approximation algorithm for constrained forest problems. Further, Sharma, Swamy, and Williamson extended this work by developing a 2.54-approximation algorithm for the prize-collecting version of these problems. Motivated by the generality of their framework, which includes problems such as Steiner trees, Steiner forests, and their variants, we pursued further exploration. We present a significant improvement by achieving a 2-approximation algorithm for this general model, matching the approximation factor of the constrained forest problems.

cs.DS↗

arXiv2025

Breaking a Long-Standing Barrier: 2-$\varepsilon$ Approximation for Steiner Forest

The Steiner Forest problem, also known as the Generalized Steiner Tree problem, is a fundamental optimization problem on edge-weighted graphs where, given a set of vertex pairs, the goal is to select a minimum-cost subgraph such that each pair is connected. This problem generalizes the Steiner Tree problem, first introduced in 1811, for which the best known approximation factor is 1.39 [Byrka, Grandoni, Rothvoß, and Sanità, 2010] (Best Paper award, STOC 2010). The celebrated work of [Agrawal, Klein, and Ravi, 1989] (30-Year Test-of-Time award, STOC 2023), along with refinements by [Goemans and Williamson, 1992] (SICOMP'95), established a 2-approximation for Steiner Forest over 35 years ago. Jain's (FOCS'98) pioneering iterative rounding techniques later extended these results to higher connectivity settings. Despite the long-standing importance of this problem, breaking the approximation factor of 2 has remained a major challenge, raising suspicions that achieving a better factor -- similar to Vertex Cover -- might indeed be hard. Notably, fundamental works, including those by Gupta and Kumar (STOC'15) and Groß et al. (ITCS'18), introduced 96- and 69-approximation algorithms, possibly with the hope of paving the way for a breakthrough in achieving a constant-factor approximation below 2 for the Steiner Forest problem. In this paper, we break the approximation barrier of 2 by designing a novel deterministic algorithm that achieves a $2 - 10^{-11}$ approximation for this fundamental problem. As a key component of our approach, we also introduce a novel dual-based local search algorithm for the Steiner Tree problem with an approximation guarantee of $1.943$, which is of independent interest.

cs.DS↗

arXiv2025

Bandit Social Learning: Exploration under Myopic Behavior

We study social learning dynamics motivated by reviews on online platforms. The agents collectively follow a simple multi-armed bandit protocol, but each agent acts myopically, without regards to exploration. We allow the greedy (exploitation-only) algorithm, as well as a wide range of behavioral biases. Specifically, we allow myopic behaviors that are consistent with (parameterized) confidence intervals for the arms' expected rewards. We derive stark learning failures for any such behavior, and provide matching positive results. The learning-failure results extend to Bayesian agents and Bayesian bandit environments. In particular, we obtain general, quantitatively strong results on failure of the greedy bandit algorithm, both for ``frequentist" and ``Bayesian" versions. Failure results known previously are quantitatively weak, and either trivial or very specialized. Thus, we provide a theoretical foundation for designing non-trivial bandit algorithms, \ie algorithms that intentionally explore, which has been missing from the literature. Our general behavioral model can be interpreted as agents' optimism or pessimism. The matching positive results entail a maximal allowed amount of optimism. Moreover, we find that no amount of pessimism helps against the learning failures, whereas even a small-but-constant fraction of extreme optimists avoids the failures and leads to near-optimal regret rates.

cs.GT↗

arXiv2025

Pandora with Inaccurate Priors

We investigate the role of inaccurate priors for the classical Pandora's box problem. In the classical Pandora's box problem we are given a set of boxes each with a known cost and an unknown value sampled from a known distribution. We investigate how inaccuracies in the beliefs can affect existing algorithms. Specifically, we assume that the knowledge of the underlying distribution has a small error in the Kolmogorov distance, and study how this affects the utility obtained by the optimal algorithm.

cs.DS↗

arXiv2025

Replication-proof Bandit Mechanism Design with Bayesian Agents

We study the problem of designing replication-proof bandit mechanisms when agents strategically register or replicate their own arms to maximize their payoff. Specifically, we consider Bayesian agents who only know the distribution from which their own arms' mean rewards are sampled, unlike the original setting of by Shin et al. 2022. Interestingly, with Bayesian agents in stark contrast to the previous work, analyzing the replication-proofness of an algorithm becomes significantly complicated even in a single-agent setting. We provide sufficient and necessary conditions for an algorithm to be replication-proof in the single-agent setting, and present an algorithm that satisfies these properties. These results center around several analytical theorems that focus on \emph{comparing the expected regret of multiple bandit instances}, and therefore might be of independent interest since they have not been studied before to the best of our knowledge. We expand this result to the multi-agent setting, and provide a replication-proof algorithm for any problem instance. We finalize our result by proving its sublinear regret upper bound which matches that of Shin et al. 2022.

cs.GT↗

arXiv2025

Beating Competitive Ratio 4 for Graphic Matroid Secretary

One of the classic problems in online decision-making is the *secretary problem* where to goal is to maximize the probability of choosing the largest number from a randomly ordered sequence. A natural extension allows selecting multiple values under a combinatorial constraint. Babaioff, Immorlica, Kempe, and Kleinberg (SODA'07, JACM'18) introduced the *matroid secretary conjecture*, suggesting an $O(1)$-competitive algorithm exists for matroids. Many works since have attempted to obtain algorithms for both general matroids and specific classes of matroids. The ultimate goal is to obtain an $e$-competitive algorithm, and the *strong matroid secretary conjecture* states that this is possible for general matroids. A key class of matroids is the *graphic matroid*, where a set of graph edges is independent if it contains no cycle. The rich combinatorial structure of graphs makes them a natural first step towards solving a problem for general matroids. Babaioff et al. (SODA'07, JACM'18) first studied the graphic matroid setting, achieving a $16$-competitive algorithm. Subsequent works have improved the competitive ratio, most recently to 4 by Soto, Turkieltaub, and Verdugo (SODA'18). We break this $4$-competitive barrier, presenting a new algorithm with a competitive ratio of $3.95$. For simple graphs, we further improve this to $3.77$. Intuitively, solving the problem for simple graphs is easier since they lack length-two cycles. A natural question is whether a ratio arbitrarily close to $e$ can be achieved by assuming sufficiently large girth. We answer this affirmatively, showing a competitive ratio arbitrarily close to $e$ even for constant girth values, supporting the strong matroid secretary conjecture. We also prove this bound is tight: for any constant $g$, no algorithm can achieve a ratio better than $e$ even when the graph has girth at least $g$.

cs.DS↗

arXiv2025

Gains-from-Trade in Bilateral Trade with a Broker

We study bilateral trade with a broker, where a buyer and seller interact exclusively through the broker. The broker strategically maximizes her payoff through arbitrage by trading with the buyer and seller at different prices. We study whether the presence of the broker interferes with the mechanism's gains-from-trade (GFT) achieving a constant-factor approximation to the first-best gains-from-trade (FB). We first show that the GFT achieves a $1 / 36$-approximation to the FB even if the broker runs an optimal posted-pricing mechanism under symmetric agents with monotone-hazard-rate distributions. Beyond posted-pricing mechanisms, even if the broker uses an arbitrary incentive-compatible (IC) and individually-rational (IR) mechanism that maximizes her expected profit, we prove that it induces a $1 / 2$-approximation to the first-best GFT when the buyer and seller's distributions are uniform distributions with arbitrary support. This bound is shown to be tight. We complement such results by proving that if the broker uses an arbitrary profit-maximizing IC and IR mechanism, there exists a family of problem instances under which the approximation factor to the first-best GFT becomes arbitrarily bad. We show that this phenomenon persists even if we restrict one of the buyer's or seller's distributions to have a singleton support, or even in the symmetric setting where the buyer and seller have identical distributions.

cs.GT↗

arXiv2024

Bi-Criteria Metric Distortion

Selecting representatives based on voters' preferences is a fundamental problem in social choice theory. While cardinal utility functions offer a detailed representation of preferences, ordinal rankings are often the only available information due to their simplicity and practical constraints. The metric distortion framework addresses this issue by modeling voters and candidates as points in a metric space, with distortion quantifying the efficiency loss from relying solely on ordinal rankings. Existing works define the cost of a voter with respect to a candidate as their distance and set the overall cost as either the sum (utilitarian) or maximum (egalitarian) of these costs across all voters. They show that deterministic algorithms achieve a best-possible distortion of 3 for any metric when considering a single candidate. This paper explores whether one can obtain a better approximation compared to an optimal candidate by relying on a committee of $k$ candidates ($k \ge 1$), where the cost of a voter is defined as its distance to the closest candidate in the committee. We answer this affirmatively in the case of line metrics, demonstrating that with $O(1)$ candidates, it is possible to achieve optimal cost. Our results extend to both utilitarian and egalitarian objectives, providing new upper bounds for the problem. We complement our results with lower bounds for both the line and 2-D Euclidean metrics.

cs.GT↗

arXiv2024

Fairness and Efficiency in Online Class Matching

The online bipartite matching problem, extensively studied in the literature, deals with the allocation of online arriving vertices (items) to a predetermined set of offline vertices (agents). However, little attention has been given to the concept of class fairness, where agents are categorized into different classes, and the matching algorithm must ensure equitable distribution across these classes. We here focus on randomized algorithms for the fair matching of indivisible items, subject to various definitions of fairness. Our main contribution is the first (randomized) non-wasteful algorithm that simultaneously achieves a $1/2$ approximation to class envy-freeness (CEF) while simultaneously ensuring an equivalent approximation to the class proportionality (CPROP) and utilitarian social welfare (USW) objectives. We supplement this result by demonstrating that no non-wasteful algorithm can achieve an $α$-CEF guarantee for $α> 0.761$. In a similar vein, we provide a novel input instance for deterministic divisible matching that demonstrates a nearly tight CEF approximation. Lastly, we define the ``price of fairness,'' which represents the trade-off between optimal and fair matching. We demonstrate that increasing the level of fairness in the approximation of the solution leads to a decrease in the objective of maximizing USW, following an inverse proportionality relationship.

cs.GT↗

arXiv2024

Online Advertisements with LLMs: Opportunities and Challenges

This paper explores the potential for leveraging Large Language Models (LLM) in the realm of online advertising systems. We introduce a general framework for LLM advertisement, consisting of modification, bidding, prediction, and auction modules. Different design considerations for each module are presented. These design choices are evaluated and discussed based on essential desiderata required to maintain a sustainable system. Further fundamental questions regarding practicality, efficiency, and implementation challenges are raised for future research. Finally, we exposit how recent approaches on mechanism design for LLM can be framed in our unified perspective.

cs.CY↗

arXiv2024

Dynamic Metric Embedding into $\ell_p$ Space

We give the first non-trivial decremental dynamic embedding of a weighted, undirected graph $G$ into $\ell_p$ space. Given a weighted graph $G$ undergoing a sequence of edge weight increases, the goal of this problem is to maintain a (randomized) mapping $ϕ: (G,d) \to (X,\ell_p)$ from the set of vertices of the graph to the $\ell_p$ space such that for every pair of vertices $u$ and $v$, the expected distance between $ϕ(u)$ and $ϕ(v)$ in the $\ell_p$ metric is within a small multiplicative factor, referred to as the \emph{distortion}, of their distance in $G$. Our main result is a dynamic algorithm with expected distortion $O(\log^3 n)$ and total update time $O\left((m^{1+o(1)} \log^2 W + Q \log n)\log(nW) \right)$, where $W$ is the maximum weight of the edges, $Q$ is the total number of updates and $n, m$ denote the number of vertices and edges in $G$ respectively. This is the first result of its kind, extending the seminal result of Bourgain to the growing field of dynamic algorithms. Moreover, we demonstrate that in the fully dynamic regime, where we tolerate edge insertions as well as deletions, no algorithm can explicitly maintain an embedding into $\ell_p$ space that has a low distortion with high probability.

cs.DS↗