49 accepted papers
With the rapid progress of multi-agent large language model (LLM) reasoning, how to effectively aggregate answers from multiple LLMs has emerged as a fundamental challenge. Standard majority voting treats all answers equally, failing to consider latent heterogeneity and correlation across models. In…
Synthetic data has been increasingly used to train frontier generative models. However, recent study raises key concerns that iteratively retraining a generative model on its self-generated synthetic data may keep deteriorating model performance, a phenomenon often coined model collapse. In this pap…
With the rapid progress of large language models (LLMs) trained on every available piece of data, it becomes increasingly challenging to reliably evaluate their intelligence due to potential data contamination and benchmark overfitting. To overcome these challenges, we investigate a new angle of ben…
Data markets promise to unlock data value by matching data suppliers with ML consumers. However, market design involves addressing intricate challenges, including data pricing, fairness, and robustness. We propose a pragmatic data-augmented AutoML market that seamlessly integrates with existing clou…
The probabilistic bisection algorithm (PBA) extends the classical binary search to settings with noisy responses, and is a foundational algorithm commonly used in basic problems such as root-finding. Despite its strong empirical success, its theoretical property, particularly the convergence rate, r…
As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives. Multi-model serving further complicates these trade-offs; for example, in cascaded models, each early-exit decis…
Researchers strategically choose where to submit their work in order to maximize its impact, and these publication decisions in turn determine venues
This paper introduces new parameter-free first-order methods for convex optimization problems in which the objective function exhibits Hölder smoothness. Inspired by the recently proposed distance-over-gradient (DOG) technique, we propose an accelerated distance-adaptive method which achieves optima…
We develop a framework for capturing the instrumental value of data production processes, which accounts for two key factors: (a) the context of the agent’s decision-making; (b) how much data or information the buyer already possesses. We "micro-found" our data valuation function by establishing its…
Online advertising platforms use automated auctions to connect advertisers with potential customers, requiring effective bidding strategies to maximize profits. Accurate ad impact estimation requires considering three key factors: delayed and long-term effects, cumulative ad impacts such as reinforc…
This paper studies Learning from Imperfect Human Feedback (LIHF), addressing the potential irrationality or imperfect perception when learning from comparative human feedback. Building on evidences that human's imperfection decays over time (i.e., humans learn to improve), we cast this problem as a…
We investigate auction mechanisms for AI-generated content, focusing on applications like ad creative generation. In our model, agents' preferences over stochastically generated content are encoded as large language models (LLMs). We propose an auction format that operates on a token-by-token basis,
In green security, defenders must forecast adversarial behavior-such as poaching, illegal logging, and illegal fishing-to plan effective patrols. These behavior are often highly uncertain and complex. Prior work has leveraged game theory to design robust patrol strategies to handle uncertainty, but
Consider public health officials aiming to spread awareness about a new vaccine in a community interconnected by a social network. How can they distribute information with minimal resources, so as to avoid polarization and ensure community-wide convergence of opinion? To tackle such challenges, we i…
We investigate the robustness of multi-agent learning in strongly monotone games with bandit feedback. While previous research has developed learning algorithms that achieve last-iterate convergence to the unique Nash equilibrium (NE) at a polynomial rate, we demonstrate that all such algorithms are…
We introduce the tokenized linear bandit (TLB) and multi-armed bandit (TMAB), variants of linear and stochastic multi-armed bandit problems inspired by LLM decoding and alignment. In these problems, at each round $t \in [T]$, a user submits a query (context), and the decision maker (DM) sequentially…
We study a strategic variant of the multi-armed bandit problem, which we coin the strategic click-bandit. This model is motivated by applications in online recommendation where the choice of recommended items depends on both the click-through rates and the post-click rewards. Like in classical bandi…
The advent of generative AI (GenAI) technology produces a transformative impact on the content creation landscape, offering alternative approaches to produce diverse, good-quality content across media, thereby reshaping online ecosystems but also raising concerns about market over-saturation and the…
To enhance the efficiency and practicality of federated bandit learning, recent advances have introduced incentives to motivate communication among clients, where a client participates only when the incentive offered by the server outweighs its participation cost. However, existing incentive mechani…
Prophet inequality concerns a basic optimal stopping problem and states that simple threshold stopping policies --- i.e., accepting the first reward larger than a certain threshold --- can achieve tight $\frac{1}{2}$-approximation to the optimal prophet value. Motivated by its economic applications,…
We study a ubiquitous learning challenge in online principal-agent problems during which the principal learns the agent's private information from the agent's revealed preferences in historical interactions. This paradigm includes important special cases such as pricing and contract design, which ha…
We consider *multiple senders* with informational advantage signaling to convince a single self-interested actor to take certain actions. Generalizing the seminal *Bayesian Persuasion* framework, such settings are ubiquitous in computational economics, multi-agent learning, and machine learning with…
Motivated by the phenomenon of strategic agents gaming a recommender system to maximize the number of times they are recommended to users, we study a strategic variant of the linear contextual bandit problem, where the arms can strategically misreport privately observed contexts to the learner. We…
On User-Generated Content (UGC) platforms, recommendation algorithms significantly impact creators' motivation to produce content as they compete for algorithmically allocated user traffic. This phenomenon subtly shapes the volume and diversity of the content pool, which is crucial for the platform'…
Standard contextual bandit problem assumes that all the relevant contexts are observed before the algorithm chooses an arm. This modeling paradigm, while useful, often falls short when dealing with problems in which additional valuable contexts can be observed after arm selection. For example, conte…
This study explores the impact of content creators' competition on user welfare in recommendation platforms, as well as the long-term dynamics of relevance-driven recommendations. We establish a model of creator competition, under the setting where the platform uses a top-$K$ recommendation policy,…
Most existing works on federated bandits take it for granted that all clients are altruistic about sharing their data with the server for the collective good whenever needed. Despite their compelling theoretical guarantee on performance and communication efficiency, this assumption is overly idealis…
The past decade has witnessed the flourishing of a new profession as media content creators, who rely on revenue streams from online content recommendation platforms. The reward mechanism employed by these platforms creates a competitive environment among creators which affects their production choi…
This survey overviews a new research agenda on the economics of machine learning, pursued at the Strategic IntelliGence for Machine Agent (SIGMA) Lab at UChicago. This overall research agenda has two themes: machine learning for economics and, conversely, economics for machine learning (ML)…
Data valuation, or the valuation of individual datum contributions, has seen growing interest in machine learning due to its demonstrable efficacy for tasks such as noisy label detection. In particular, due to the desirable axiomatic properties, several Shapley value approximations have been propose…
This paper studies a function fitting problem which we coin first-order convex fitting (FCF): given any two vector sequences x1, ..., xT and p1, ..., pT, when is it possible to efficiently construct a convex function f(x) that ``fits'' the two sequences in the first-order sense, i.e, the (sub)g…
Incrementality, which measures the causal effect of showing an ad to a potential customer (e.g. a user in an internet platform) versus not, is a central object for advertisers in online advertising platforms. This paper investigates the problem of how an advertiser can learn to optimize the biddin…
This paper studies the problem of information design in a general security game setting in which multiple independent self-interested defenders attempt to provide protection simultaneously on the same set of important targets against an unknown attacker. A principal, who can be one of the defenders,…
Optimizing strategic decisions (a.k.a. computing equilibrium) is key to the success of many non-cooperative multi-agent applications. However, in many real-world situations, we may face the exact opposite of this game-theoretic problem --- instead of prescribing equilibrium of a given game, we may d…
In real-world recommendation problems, especially those with a formidably large item space, users have to gradually learn to estimate the utility of any fresh recommendations from their experience about previously consumed items. This in turn affects their interaction dynamics with the system and ca…
We propose a new problem setting to study the sequential interactions between a recommender system and a user. Instead of assuming the user is omniscient, static, and explicit, as the classical practice does, we sketch a more realistic user behavior model, under which the user: 1) rejects recommenda…
This paper studies bandit algorithms under data poisoning attacks in a bounded reward setting. We consider a strong attacker model in which the attacker can observe both the selected actions and their corresponding rewards, and can contaminate the rewards with additive noise. We show that any bandit…
We consider a new problem of selling data to a machine learner who looks to purchase data to train his machine learning model. A key challenge in this setup is that neither the seller nor the machine learner knows the true quality of data. When designing a revenue-maximizing mechanism, a data seller…
We study the second-price auction in which bidders have asymmetric information regarding the item’s value. Each bidder’s value for the item depends on a private component and a public component. While each bidder observes their own private component, they hold different and asymmetric information ab…
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate any order-optimal learning algorithm towards a targeted policy in episodic RL and examines the potential damage of two natural types of poisoning attacks, i.e., the manip…
We study adversarial attacks on linear stochastic bandits: by manipulating the rewards, an adversary aims to control the behaviour of the bandit algorithm. Perhaps surprisingly, we first show that some attack goals can never be achieved. This is in a sharp contrast to context-free stochastic bandits…
This paper studies defender patrol deception in general Stackelberg security games (SSGs), where a defender attempts to alter the attacker's perception of the defender's patrolling intensity so as to influence the attacker's decision making. We are interested in understanding the complexity and effe…
Incentivized exploration in multi-armed bandits (MAB) has witnessed increasing interests and many progresses in recent years, where a principal offers bonuses to agents to do explorations on her behalf. However, almost all existing studies are confined to temporary myopic agents. In this work, we br…
Diffusion source identification on networks is a problem of fundamental importance in a broad class of applications, including controlling the spreading of rumors on social media, identifying a computer virus over cyber networks, or identifying the disease center during epidemiology. Though this pro…
Peer review systems such as conference paper review often suffer from the issue of miscalibration. Previous works on peer review calibration usually only use the ordinal information or assume simplistic reviewer scoring functions such as linear functions. In practice, applications like academic conf…
The study of strategic or adversarial manipulation of testing data to fool a classifier has attracted much recent attention. Most previous works have focused on two extreme situations where any testing data point either is completely adversarial or always equally prefers the positive label. In this…
A ubiquitous learning problem in today’s digital market is, during repeated interactions between a seller and a buyer, how a seller can gradually learn optimal pricing decisions based on the buyer’s past purchase responses. A fundamental challenge of learning in such a strategic setup is that the bu…
We propose and study Collapsing Bandits, a new restless multi-armed bandit (RMAB) setting in which each arm follows a binary-state Markovian process with a special structure: when an arm is played, the state is fully observed, thus“collapsing” any uncertainty, but when an arm is passive, no observa…
Motivated by economic applications such as recommender systems, we study the behavior of stochastic bandits algorithms under \emph{strategic behavior} conducted by rational actors, i.e., the arms. Each arm is a \emph{self-interested} strategic player who can modify its own reward whenever pulled, su…