Online Learning via Offline Greedy Algorithms: Applications in Market Design and Optimization

by   Rad Niazadeh, et al.

Motivated by online decision-making in time-varying combinatorial environments, we study the problem of transforming offline algorithms to their online counterparts. We focus on offline combinatorial problems that are amenable to a constant factor approximation using a greedy algorithm that is robust to local errors. For such problems, we provide a general framework that efficiently transforms offline robust greedy algorithms to online ones using Blackwell approachability. We show that the resulting online algorithms have O(√(T)) (approximate) regret under the full information setting. We further introduce a bandit extension of Blackwell approachability that we call Bandit Blackwell approachability. We leverage this notion to transform greedy robust offline algorithms into a O(T^2/3) (approximate) regret in the bandit setting. Demonstrating the flexibility of our framework, we apply our offline-to-online transformation to several problems at the intersection of revenue management, market design, and online optimization, including product ranking optimization in online platforms, reserve price optimization in auctions, and submodular maximization. We show that our transformation, when applied to these applications, leads to new regret bounds or improves the current known bounds.


page 1

page 2

page 3

page 4


General Transformation for Consistent Online Approximation Algorithms

We introduce a transformation framework that can be utilized to develop ...

Online Improper Learning with an Approximation Oracle

We revisit the question of reducing online learning to approximate optim...

Multi-layered Network Exploration via Random Walks: From Offline Optimization to Online Learning

Multi-layered network exploration (MuLaNE) problem is an important probl...

On Local Regret

Online learning aims to perform nearly as well as the best hypothesis in...

The Bayesian Prophet: A Low-Regret Framework for Online Decision Making

Motivated by the success of using black-box predictive algorithms as sub...

Community Exploration: From Offline Optimization to Online Learning

We introduce the community exploration problem that has many real-world ...

Combining Offline Causal Inference and Online Bandit Learning for Data Driven Decisions

A fundamental question for companies is: How to make good decisions with...

Please sign up or login with your details

Forgot password? Click here to reset