Prediction-sharing During Training and Inference

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gafni, Yotam, Gradwohl, Ronen, Tennenholtz, Moshe
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866907843126362112
author Gafni, Yotam
Gradwohl, Ronen
Tennenholtz, Moshe
author_facet Gafni, Yotam
Gradwohl, Ronen
Tennenholtz, Moshe
contents Two firms are engaged in a competitive prediction task. Each firm has two sources of data -- labeled historical data and unlabeled inference-time data -- and uses the former to derive a prediction model, and the latter to make predictions on new instances. We study data-sharing contracts between the firms. The novelty of our study is to introduce and highlight the differences between contracts that share prediction models only, contracts to share inference-time predictions only, and contracts to share both. Our analysis proceeds on three levels. First, we develop a general Bayesian framework that facilitates our study. Second, we narrow our focus to two natural settings within this framework: (i) a setting in which the accuracy of each firm's prediction model is common knowledge, but the correlation between the respective models is unknown; and (ii) a setting in which two hypotheses exist regarding the optimal predictor, and one of the firms has a structural advantage in deducing it. Within these two settings we study optimal contract choice. More specifically, we find the individually rational and Pareto-optimal contracts for some notable cases, and describe specific settings where each of the different sharing contracts emerge as optimal. Finally, in the third level of our analysis we demonstrate the applicability of our concepts in a synthetic simulation using real loan data.
format Preprint
id arxiv_https___arxiv_org_abs_2403_17515
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prediction-sharing During Training and Inference
Gafni, Yotam
Gradwohl, Ronen
Tennenholtz, Moshe
Theoretical Economics
Artificial Intelligence
Computer Science and Game Theory
Machine Learning
Multiagent Systems
Two firms are engaged in a competitive prediction task. Each firm has two sources of data -- labeled historical data and unlabeled inference-time data -- and uses the former to derive a prediction model, and the latter to make predictions on new instances. We study data-sharing contracts between the firms. The novelty of our study is to introduce and highlight the differences between contracts that share prediction models only, contracts to share inference-time predictions only, and contracts to share both. Our analysis proceeds on three levels. First, we develop a general Bayesian framework that facilitates our study. Second, we narrow our focus to two natural settings within this framework: (i) a setting in which the accuracy of each firm's prediction model is common knowledge, but the correlation between the respective models is unknown; and (ii) a setting in which two hypotheses exist regarding the optimal predictor, and one of the firms has a structural advantage in deducing it. Within these two settings we study optimal contract choice. More specifically, we find the individually rational and Pareto-optimal contracts for some notable cases, and describe specific settings where each of the different sharing contracts emerge as optimal. Finally, in the third level of our analysis we demonstrate the applicability of our concepts in a synthetic simulation using real loan data.
title Prediction-sharing During Training and Inference
topic Theoretical Economics
Artificial Intelligence
Computer Science and Game Theory
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2403.17515