Online Allocation and Learning in the Presence of Strategic Agents
Authors: Steven Yin, Shipra Agrawal, Assaf Zeevi
NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We present an online allocation mechanism that is approximately-BIC, and further achieves low regret guarantees on individual regret when all agents are truthful. Our algorithm contains two components: a learner, and a detector. ... Our main results are the following guarantees on incentive compatibility and regret of our online allocation algorithm. Theorem 1 (Approximate-BIC). Algorithm 1 is (O(n T log(n T/δ)), δ)-approximate BIC. ... Theorem 2 (Individual Regret). ... All the missing details of the proofs are provided in the appendix. Finally, in Section 7 we discuss some limitations and future directions. |
| Researcher Affiliation | Academia | Steven Yin Department of Industrial Engineering and Operations Research Columbia University New York, NY 10027 sy2737@columbia.edu Shipra Agrawal Department of Industrial Engineering and Operations Research Columbia University New York, NY 10027 sa3305@columbia.edu Assaf Zeevi Graduate School of Business Columbia University New York, NY 10027 assaf@gsb.columbia.edu |
| Pseudocode | Yes | Algorithm 1: Epoch Based Online Allocation Algorithm Algorithm 2: Detection Algorithm |
| Open Source Code | No | Did you include the code, data, and instructions needed to reproduce the main experi- mental results (either in the supplemental material or as a URL)? [N/A] |
| Open Datasets | No | The paper is theoretical and does not involve the use of datasets for training. The checklist explicitly states N/A for experimental results. |
| Dataset Splits | No | The paper is theoretical and does not involve empirical validation splits. The checklist explicitly states N/A for experimental results. |
| Hardware Specification | No | The paper is theoretical and does not describe experiments that would require hardware specifications. The checklist explicitly states N/A for experimental results. |
| Software Dependencies | No | The paper is theoretical and does not describe experiments that would require software dependencies. The checklist explicitly states N/A for experimental results. |
| Experiment Setup | No | The paper is theoretical and does not describe an experimental setup with hyperparameters or training settings. The checklist explicitly states N/A for experimental results. |