1 citations · 1 across the 10 of their papers we have counts for
12 papers
Pairwise Exchanges of Freely Replicable Goods with Negative Externalities
Shangyuan Yang, Kirthevasan Kandasamy
We study a setting where a set of agents engage in pairwise exchanges of freely replicable goods (e.g., digital goods such as data), where two agents grant each other a copy of a g…
Learning from Biased and Costly Data Sources: Minimax-optimal Data Collection under a Budget
Michael O. Harding, Vikas Singh, Kirthevasan Kandasamy
Data collection is a critical component of modern statistical and machine learning pipelines, particularly when data must be gathered from multiple heterogeneous sources to study a…
Strategy-robust Online Learning in Contextual Pricing
Joon Suk Huh, Kirthevasan Kandasamy
Learning effective pricing strategies is crucial in digital marketplaces, especially when buyers' valuations are unknown and must be inferred through interaction. We study online c…
Constrained Best Arm Identification with Tests for Feasibility
Ting Cai, Kirthevasan Kandasamy
Best arm identification (BAI) aims to identify the highest-performance arm among a set of arms by collecting stochastic samples from each arm. In real-world problems, the best…
Agora: A System for Consumption-Based GPU Pricing
Ian McDougall, Noah Scott, Joon Huh +2
We present Agora, a lightweight system designed for cloud-based GPUs which meters a three-dimensional resource vector from commodity performance counters and prices it with a funct…
A Cramér-von Mises Approach to Incentivizing Truthful Data Sharing
Alex Clinton, Thomas Zeng, Yiding Chen +2
Modern data marketplaces and data sharing consortia increasingly rely on incentive mechanisms to encourage agents to contribute data. However, schemes that reward agents based on t…
Balancing Performance and Costs in Best Arm Identification
Michael O. Harding, Kirthevasan Kandasamy
We consider the problem of identifying the best arm in a multi-armed bandit model. Despite a wealth of literature in the traditional fixed budget and fixed confidence regimes of th…
Incentivizing Truthful Data Contributions in a Marketplace for Mean Estimation
Keran Chen, Alex Clinton, Kirthevasan Kandasamy
We study a data marketplace where a broker intermediates between buyers, who seek to estimate the mean \(μ\) of an unknown normal distribution \(\Ncal(μ, σ^2)\), and contributors,…
Nash Incentive-compatible Online Mechanism Learning via Weakly Differentially Private Online Learning
Joon Suk Huh, Kirthevasan Kandasamy
We study a multi-round mechanism design problem, where we interact with a set of agents over a sequence of rounds. We wish to design an incentive-compatible (IC) online learning sc…
Collaborative Mean Estimation Among Heterogeneous Strategic Agents: Individual Rationality, Fairness, and Truthful Contribution
Alex Clinton, Yiding Chen, Xiaojin Zhu +1
We study a collaborative learning problem where agents aim to estimate a vector by sampling from associated univariate normal distributions…
Learning to Price Homogeneous Data
Keran Chen, Joon Suk Huh, Kirthevasan Kandasamy
We study a data pricing problem, where a seller has access to homogeneous data points (e.g. drawn i.i.d. from some distribution). There are types of buyers in the market, w…
Bandit Profit-maximization for Targeted Marketing
Joon Suk Huh, Ellen Vitercik, Kirthevasan Kandasamy
We study a sequential profit-maximization problem, optimizing for both price and ancillary variables like marketing expenditures. Specifically, we aim to maximize profit over an ar…