Search Results for author:
Found 48 papers, 8 papers with code
Grounded Persuasive Language Generation for Automated Marketing
This paper develops an agentic framework that employs large language models (LLMs) to automate the generation of persuasive and grounded marketing content, using real estate listing descriptions as our focal application domain.
Robust Optimization with Diffusion Models for Green Security
To the best of our knowledge, this is the first application of diffusion models in the green security domain.
Machine Learning Should Maximize Welfare, Not (Only) Accuracy
Decades of research in machine learning have given us powerful tools for making accurate predictions.
On Sequential Fault-Intolerant Process Planning
We propose and study a planning problem we call Sequential Fault-Intolerant Process Planning (SFIPP).
An Instrumental Value for Data Production and its Application to Data Pricing
When instantiated in the domain of Bayesian linear regression, our value naturally corresponds to information gain.
Data-Driven Mechanism Design: Jointly Eliciting Preferences and Information
We study mechanism design when agents hold private information about both their preferences and a common payoff-relevant state.
IRL for Restless Multi-Armed Bandits with Applications in Maternal and Child Health
To address this shortcoming, this paper is the first to present the use of inverse reinforcement learning (IRL) to learn desired rewards for RMABs, and we demonstrate improved outcomes in a maternal and child health telehealth program.
Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms
In this work, we demonstrate, both theoretically and empirically, that a purely relevance-driven policy with low exploration strength boosts short-term user satisfaction but undermines the long-term richness of the content pool.
Contractual Reinforcement Learning: Pulling Arms with Invisible Hands
The agency problem emerges in today's large scale machine learning tasks, where the learners are unable to direct content creation or enforce data collection.
How to Strategize Human Content Creation in the Era of GenAI?
In time-sensitive content domains (e. g., news or pop music creation) where contents' value diminishes over time, we show that there is no polynomial time algorithm for finding the human's optimal (dynamic) strategy, unless the randomized exponential time hypothesis is false.
Strategic Linear Contextual Bandits
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.
Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Dueling
This paper studies Learning from Imperfect Human Feedback (LIHF), addressing the potential irrationality or imperfect perception when learning from comparative human feedback.
User Welfare Optimization in Recommender Systems with Competing Content Creators
Driven by the new economic opportunities created by the creator economy, an increasing number of content creators rely on and compete for revenue generated from online content recommendation platforms.
Multi-Sender Persuasion: A Computational Perspective
We consider the multi-sender persuasion problem: multiple players with informational advantage signal to convince a single self-interested actor to take certain actions.
Incentivized Truthful Communication for Federated Bandits
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.
Learning in Online Principal-Agent Interactions: The Power of Menus
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.
Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
We study a strategic variant of the multi-armed bandit problem, which we coin the strategic click-bandit.
Sample Complexity of Linear Regression Models for Opinion Formation in Networks
Second, we leverage this optimization to study the network gain which measures the improvement of sample complexity when learning over a network compared to that in isolation.
A Data-Centric Online Market for Machine Learning: From Discovery to Pricing
We envision that the synergy of our data and model discovery algorithm and pricing mechanism will be an important step towards building a new data-centric online market that serves ML users effectively.
How Bad is Top-$K$ Recommendation under Competing Content Creators?
Content creators compete for exposure on recommendation platforms, and such strategic behavior leads to a dynamic shift over the content distribution.
Multi-Player Bandits Robust to Adversarial Collisions
We provide the first decentralized and robust algorithm RESYNC for defenders whose performance deteriorates gracefully as $\tilde{O}(C)$ as the number of collisions $C$ from the attackers increases.
CS-Shapley: Class-wise Shapley Values for Data Valuation in Classification
Our theoretical analysis shows the proposed value function is (essentially) the unique function that satisfies two desirable properties for evaluating data values in classification.
Learning Correlated Stackelberg Equilibrium in General-Sum Multi-Leader-Single-Follower Games
Many real-world strategic games involve interactions between multiple players.
Understanding the Limits of Poisoning Attacks in Episodic Reinforcement Learning
To understand the security threats to reinforcement learning (RL) algorithms, this paper studies poisoning attacks to manipulate \emph{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 manipulation of \emph{reward} and \emph{action}.
Incrementality Bidding via Reinforcement Learning under Mixed and Delayed Rewards
Incrementality, which is used to measure 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.
Sequential Information Design: Markov Persuasion Process and Its Efficient Reinforcement Learning
This paper proposes a novel model of sequential information design, namely the Markov persuasion processes (MPPs), where a sender, with informational advantage, seeks to persuade a stream of myopic receivers to take actions that maximizes the sender's cumulative utilities in a finite horizon Markovian environment with varying prior and utility functions.
Online Bayesian Recommendation with No Regret
For each user with her own private preference and belief, the platform commits to a recommendation strategy to utilize his information advantage on the product state to persuade the self-interested user to follow the recommendation.
Learning from a Learning User for Optimal Recommendations
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.
Least Square Calibration for Peer Reviews
Peer review systems such as conference paper review often suffer from the issue of miscalibration.
Uncoupled Bandit Learning towards Rationalizability: Benchmarks, Barriers, and Algorithms
Under the uncoupled learning setup, the last-iterate convergence guarantee towards Nash equilibrium is shown to be impossible in many games.
(Almost) Free Incentivized Exploration from Decentralized Learning Agents
In this work, we break this barrier and study incentivized exploration with multiple and long-term strategic agents, who have more complicated behaviors that often appear in real-world applications.
Least Square Calibration for Peer Review
Peer review systems such as conference paper review often suffer from the issue of miscalibration.
When Are Linear Stochastic Bandits Attackable?
We study adversarial attacks on linear stochastic bandits: by manipulating the rewards, an adversary aims to control the behaviour of the bandit algorithm.
Learning the Optimal Recommendation from Explorative Users
We propose a new problem setting to study the sequential interactions between a recommender system and a user.
Algorithmic Information Design in Multi-Player Games: Possibility and Limits in Singleton Congestion
This paper initiates the algorithmic information design of both \emph{public} and \emph{private} signaling in a fundamental class of games with negative externalities, i. e., singleton congestion games, with wide application in today's digital economy, machine scheduling, routing, etc.
Diffusion Source Identification on Networks with Statistical Confidence
Diffusion source identification on networks is a problem of fundamental importance in a broad class of applications, including rumor controlling and virus identification.
Incentivizing Exploration in Linear Bandits under Information Gap
We study the problem of incentivizing exploration for myopic users in linear bandits, where the users tend to exploit arm with the highest predicted reward instead of exploring.
Learning to Persuade on the Fly: Robustness Against Ignorance
Motivated by information sharing in online platforms, we study repeated persuasion between a sender and a stream of receivers where at each time, the sender observes a payoff-relevant state drawn independently and identically from an unknown distribution, and shares state information with the receivers who each choose an action.
Saving Stochastic Bandits from Poisoning Attacks via Limited Data Verification
In particular, for the case of unlimited verifications, we show that with $O(\log T)$ expected number of verifications, a simple modified version of the ETC type bandit algorithm can restore the order optimal $O(\log T)$ regret irrespective of the amount of contamination used by the attacker.
PAC-Learning for Strategic Classification
In this paper, we generalize both of these through a unified framework for strategic classification, and introduce the notion of strategic VC-dimension (SVC) to capture the PAC-learnability in our general strategic setup.
Collapsing Bandits and Their Application to Public Health Intervention
Our main contributions are as follows: (i) Building on the Whittle index technique for RMABs, we derive conditions under which the Collapsing Bandits problem is indexable.
Collapsing Bandits and Their Application to Public Health Interventions
(ii) We exploit the optimality of threshold policies to build fast algorithms for computing the Whittle index, including a closed-form.
The Intrinsic Robustness of Stochastic Bandits to Strategic Manipulation
We prove that all three algorithms achieve a regret upper bound $\mathcal{O}(\max \{ B, K\ln T\})$ where $B$ is the total budget across arms, $K$ is the total number of arms and $T$ is length of the time horizon.
Human Spermbots for Cancer-Relevant Drug Delivery
Here, we successfully load human sperm with a chemotherapeutic drug and perform treatment of relevant 3D cervical cancer and patient-representative 3D ovarian cancer cell cultures, resulting in strong anti-cancer effects.
Mitigating the Curse of Correlation in Security Games by Entropy Maximization
To mitigate this issue, we propose to design entropy-maximizing defending strategies for spatio-temporal security games, which frequently suffer from CoC.
Using Social Networks to Aid Homeless Shelters: Dynamic Influence Maximization under Uncertainty - An Extended Version
This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth.
Security Games with Information Leakage: Modeling and Computation
Our experiments confirm the necessity of handling information leakage and the advantage of our algorithms.
