Bandit Data-driven Optimization: AI for Social Good and Beyond

by   Zheyuan Ryan Shi, et al.

The use of machine learning (ML) systems in real-world applications entails more than just a prediction algorithm. AI for social good applications, and many real-world ML tasks in general, feature an iterative process which joins prediction, optimization, and data acquisition happen in a loop. We introduce bandit data-driven optimization, the first iterative prediction-prescription framework to formally analyze this practical routine. Bandit data-driven optimization combines the advantages of online bandit learning and offline predictive analytics in an integrated framework. It offers a flexible setup to reason about unmodeled policy objectives and unforeseen consequences. We propose PROOF, the first algorithm for this framework and show that it achieves no-regret. Using numerical simulations, we show that PROOF achieves superior performance over existing baseline.


page 1

page 2

page 3

page 4


Thompson Sampling for Contextual Bandit Problems with Auxiliary Safety Constraints

Recent advances in contextual bandit optimization and reinforcement lear...

Online Bandit Linear Optimization: A Study

This article introduces the concepts around Online Bandit Linear Optimiz...

DQSOps: Data Quality Scoring Operations Framework for Data-Driven Applications

Data quality assessment has become a prominent component in the successf...

DataPerf: Benchmarks for Data-Centric AI Development

Machine learning (ML) research has generally focused on models, while th...

Building a Foundation for Data-Driven, Interpretable, and Robust Policy Design using the AI Economist

Optimizing economic and public policy is critical to address socioeconom...

Optimizing Interactive Systems via Data-Driven Objectives

Effective optimization is essential for real-world interactive systems t...

Lightweight Automated Feature Monitoring for Data Streams

Monitoring the behavior of automated real-time stream processing systems...

Please sign up or login with your details

Forgot password? Click here to reset